lastmanupinc-hub avatar

Axis Iliad - Codebase Intelligence For Agentic Commerce

lastmanupinc-hub/axis-iliad

Points at any GitHub repo and generates 102 artifacts across 18 programs: AGENTS.md and .cursorrules for onboarding LLMs, debug playbooks for incident response, context maps for search, MCP configs, and Visa AP2 compliance docs for agentic commerce. Exposes a streamable HTTP MCP server with tools like analyze_repository, discover_agentic_purchasing_needs, and get_project_artifacts. Free tier covers Search, Skills, and Debug programs. Pro unlocks frontend audits, SEO rules, brand guidelines, Remotion scripts, and algorithmic art generators. The API accepts budget negotiation headers if you want lite mode summaries instead of full artifact packs. Useful when you need to hand a new codebase to an agent or prepare checkout flows for autonomous purchasing.

tools
44
auth
Secret needed
transport
HTTP
last updated
Oct 14, 2026

Install

From registry metadata
$ npx add-mcp https://api.iliad.trustfabric.ai/mcp --name axis-toolbox --header 'Authorization: Bearer ${API_TOKEN}'

Run in your terminal. add-mcp asks which agents to add it to, then asks for each value it needs. Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http axis-toolbox https://api.iliad.trustfabric.ai/mcp --header 'Authorization: YOUR_AUTHORIZATION'

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 44 tools

Verified live against the running server on Nov 6, 2026.

analyze_repoAnalyze a GitHub repository and generate 152 structured AXIS artifacts across 21 programs. Returns snapshot_id plus an artifacts listing; use get_artifact to read files and get_snapshot to re-enumerate outputs without re-running analysis. Requires Authorization: Bearer <api_ke...1 params

Analyze a GitHub repository and generate 152 structured AXIS artifacts across 21 programs. Returns snapshot_id plus an artifacts listing; use get_artifact to read files and get_snapshot to re-enumerate outputs without re-running analysis. Requires Authorization: Bearer <api_ke...

Parameters* required
github_url*string
GitHub repository URL (https://github.com/owner/repo)
analyze_filesAnalyze source files directly and generate the full 152-artifact AXIS bundle without using GitHub. Returns snapshot_id plus artifact listing; use this for local, generated, or unsaved code. Requires Authorization: Bearer <api_key>. Pricing: $3.00 standard, $25 engineer per run...5 params

Analyze source files directly and generate the full 152-artifact AXIS bundle without using GitHub. Returns snapshot_id plus artifact listing; use this for local, generated, or unsaved code. Requires Authorization: Bearer <api_key>. Pricing: $3.00 standard, $25 engineer per run...

Parameters* required
files*array
Source files to analyze
frameworks*array
Detected or known frameworks
goals*array
Analysis goals
project_name*string
Name of the project
project_type*string
Project type (web_application, api_service, cli_tool, library, monorepo)
list_programsInventory mode. List all 21 AXIS programs, their generators, pricing tier, and artifact paths. Free, no auth, and no side effects. Use search_and_discover_tools instead when you only have a keyword, or get_install_manifest when you need install and onboarding metadata.

Inventory mode. List all 21 AXIS programs, their generators, pricing tier, and artifact paths. Free, no auth, and no side effects. Use search_and_discover_tools instead when you only have a keyword, or get_install_manifest when you need install and onboarding metadata.

No parameters. Call it with no arguments.

get_snapshotRetrieve status and the full artifact listing for a prior analysis by snapshot_id. Use this to re-enumerate artifact paths without re-running analysis. Snapshots created with an API key are scoped to that same account — pass the same Authorization: Bearer <api_key> used to cre...1 params

Retrieve status and the full artifact listing for a prior analysis by snapshot_id. Use this to re-enumerate artifact paths without re-running analysis. Snapshots created with an API key are scoped to that same account — pass the same Authorization: Bearer <api_key> used to cre...

Parameters* required
snapshot_id*string
Snapshot ID returned by analyze_repo or analyze_files
delete_snapshotPermanently delete a snapshot and everything derived from it (context map, repo profile, generated artifacts, search index entries). Same account scoping as get_snapshot: an anonymous (never-authenticated) snapshot is freely deletable by any caller, but an account-owned one re...1 params

Permanently delete a snapshot and everything derived from it (context map, repo profile, generated artifacts, search index entries). Same account scoping as get_snapshot: an anonymous (never-authenticated) snapshot is freely deletable by any caller, but an account-owned one re...

Parameters* required
snapshot_id*string
Snapshot ID returned by analyze_repo, analyze_files, or get_snapshot
get_artifactRead one generated artifact by snapshot_id and path. Requires access to the snapshot and may return snapshot-not-found, invalid-path, or artifact-not-found errors. Example: snapshot_id=abc-123, path=AGENTS.md. Use this when you need the full text of one artifact. Use get_snaps...2 params

Read one generated artifact by snapshot_id and path. Requires access to the snapshot and may return snapshot-not-found, invalid-path, or artifact-not-found errors. Example: snapshot_id=abc-123, path=AGENTS.md. Use this when you need the full text of one artifact. Use get_snaps...

Parameters* required
path*string
Artifact file path as returned in the artifacts list
snapshot_id*string
Snapshot ID
prepare_agentic_purchasing_previewCompute a free Purchasing Readiness Score (0-100) and gap list for a codebase without generating artifacts. No auth, no charge, no snapshot persisted. Hard caps: 25 files / 50KB per file / 1MB total. Returns score, risk_level, top gaps, frameworks detected, and which AXIS prog...4 params

Compute a free Purchasing Readiness Score (0-100) and gap list for a codebase without generating artifacts. No auth, no charge, no snapshot persisted. Hard caps: 25 files / 50KB per file / 1MB total. Returns score, risk_level, top gaps, frameworks detected, and which AXIS prog...

Parameters* required
files*array
Source files to triage (max 25 files, 50KB each, 1MB total)
frameworksarray
Optional framework hints
project_name*string
Name of the project being previewed
project_typestring
Optional project type hint (web_application, api_service, cli_tool, library, monorepo)
prepare_agentic_purchasingPrepare a codebase for agentic purchasing and return a readiness score plus commerce artifacts. Requires Authorization: Bearer <api_key>; paid analysis records a new snapshot and may return auth, quota, payment, file-limit, or validation errors. Pricing: $3.00 standard, $1.00...11 params

Prepare a codebase for agentic purchasing and return a readiness score plus commerce artifacts. Requires Authorization: Bearer <api_key>; paid analysis records a new snapshot and may return auth, quota, payment, file-limit, or validation errors. Pricing: $3.00 standard, $1.00...

Parameters* required
agent_typestring
Consuming agent type hint
budget_per_run_centsnumber
Agent budget for this call in cents
files*array
Array of {path, content} objects representing source files
focusstring
Analysis focus (default: purchasing)one of full · purchasing · security · optimization
focus_areasarray
Compliance focus areas, recorded and echoed back in the response for the caller's own reference — does not filter which artifacts are generated.
frameworks*array
Detected or known frameworks
goals*array
Project goals
project_name*string
Name of the project
project_type*string
Project type (web_application, api_service, cli_tool, library, monorepo)
referral_tokenstring
Optional referral token from another agent
spending_windowstring
Agent spending windowone of per_call · hourly · daily · monthly
closerPackage an existing AXIS snapshot (create one first via analyze_repo, analyze_files, or prepare_agentic_purchasing) into complete professional packaging + marketplace certification artifacts so a 70-80%-complete project is ready to ship and sell. Requires Authorization: Bearer...5 params

Package an existing AXIS snapshot (create one first via analyze_repo, analyze_files, or prepare_agentic_purchasing) into complete professional packaging + marketplace certification artifacts so a 70-80%-complete project is ready to ship and sell. Requires Authorization: Bearer...

Parameters* required
product_namestring
Optional branding override for product name
project_rootstring
Optional local project root path hint (metadata only in remote MCP mode)
snapshot_id*string
Existing AXIS snapshot_id to package into a distributable product
taglinestring
Optional branding tagline
target_marketplacesarray
Optional marketplaces list (e.g. npm, unreal, vscode, dockerhub, github-marketplace)
deployGenerate a zero-pipeline-minutes deploy bundle: stack-aware Dockerfile, .dockerignore, dev compose, render.yaml (Render existing-image), wrangler.pages.toml + wrangler.containers.toml + worker.ts (Cloudflare), bash/PowerShell push scripts, and a qualification report. The proje...1 params

Generate a zero-pipeline-minutes deploy bundle: stack-aware Dockerfile, .dockerignore, dev compose, render.yaml (Render existing-image), wrangler.pages.toml + wrangler.containers.toml + worker.ts (Cloudflare), bash/PowerShell push scripts, and a qualification report. The proje...

Parameters* required
snapshot_id*string
Existing AXIS snapshot_id to package into deploy artifacts
search_and_discover_toolsSearch AXIS programs by keyword and return ranked matches with artifact paths. Free, no auth, and no stateful side effects. Example: q=checkout returns commerce-relevant programs first. Use this when you know the outcome you want but not the right program. Use list_programs in...2 params

Search AXIS programs by keyword and return ranked matches with artifact paths. Free, no auth, and no stateful side effects. Example: q=checkout returns commerce-relevant programs first. Use this when you know the outcome you want but not the right program. Use list_programs in...

Parameters* required
programstring
Optional: filter results to a specific program name
qstring
Search query — keyword or phrase
get_install_manifestGet AXIS install metadata, pricing, and a shareable manifest for onboarding a new integration — MCP endpoint, per-client config for Claude Desktop/Cursor/VS Code, and the full tool catalog with pricing. Free, no auth, and no mutation beyond read access. Example: call before wi...

Get AXIS install metadata, pricing, and a shareable manifest for onboarding a new integration — MCP endpoint, per-client config for Claude Desktop/Cursor/VS Code, and the full tool catalog with pricing. Free, no auth, and no mutation beyond read access. Example: call before wi...

No parameters. Call it with no arguments.

ping_paymentExercise the real x402 payment-flow loop at a nominal $0.01 — the cheapest metered call on this server, priced just above $0 so the probe can't be run up for free without limit. Call it once with no payment credential (no auth required) to receive a 402-style payment_required...

Exercise the real x402 payment-flow loop at a nominal $0.01 — the cheapest metered call on this server, priced just above $0 so the probe can't be run up for free without limit. Call it once with no payment credential (no auth required) to receive a 402-style payment_required...

No parameters. Call it with no arguments.

improve_my_agent_with_axisAnalyze an agent codebase and return a prioritized AXIS hardening plan. Requires Authorization: Bearer <api_key> but has no usage charge on any tier — free and unmetered, unlike most AXIS tools. This creates a snapshot and may return auth, quota, file-limit, or validation erro...2 params

Analyze an agent codebase and return a prioritized AXIS hardening plan. Requires Authorization: Bearer <api_key> but has no usage charge on any tier — free and unmetered, unlike most AXIS tools. This creates a snapshot and may return auth, quota, file-limit, or validation erro...

Parameters* required
files*array
Source files of the agent to analyze
project_name*string
Name of the agent/project to improve
discover_agentic_purchasing_needsDiscover the best AXIS workflow for a purchasing or compliance task. Free, no auth, and logs lightweight task metadata for intent analytics. Example: task_description='prepare for autonomous Visa checkout'. Use this when you need commerce-specific triage and next-step guidance...3 params

Discover the best AXIS workflow for a purchasing or compliance task. Free, no auth, and logs lightweight task metadata for intent analytics. Example: task_description='prepare for autonomous Visa checkout'. Use this when you need commerce-specific triage and next-step guidance...

Parameters* required
current_readinessnumber
Optional: current Purchasing Readiness Score (0-100) if known
focus_areasarray
Optional: specific areas to focus on
task_descriptionstring
What the agent is trying to accomplish
discover_estate_toolsList sibling AXIS properties (payments via PAI'D, 3D avatar generation via AXIS Foundry, and more) — each entry gives its own MCP endpoint, auth mode, and vendored tool prices, so you can call them directly. Free, no auth, no side effects. Same data as GET /.well-known/axis-es...

List sibling AXIS properties (payments via PAI'D, 3D avatar generation via AXIS Foundry, and more) — each entry gives its own MCP endpoint, auth mode, and vendored tool prices, so you can call them directly. Free, no auth, no side effects. Same data as GET /.well-known/axis-es...

No parameters. Call it with no arguments.

get_referral_codeGet or create the caller's AXIS referral token. Requires Authorization: Bearer <api_key>, has no usage charge, and may persist a new referral code if one does not exist yet. Example: call before sharing AXIS with another agent or workspace. Use this when you need the shareable...

Get or create the caller's AXIS referral token. Requires Authorization: Bearer <api_key>, has no usage charge, and may persist a new referral code if one does not exist yet. Example: call before sharing AXIS with another agent or workspace. Use this when you need the shareable...

No parameters. Call it with no arguments.

get_referral_creditsGet the caller's referral earnings, milestones, and free-call status. Requires Authorization: Bearer <api_key>, has no usage charge, and returns the current discount ledger without creating a new analysis. Example: call after a referral campaign to inspect earned credits. Use...

Get the caller's referral earnings, milestones, and free-call status. Requires Authorization: Bearer <api_key>, has no usage charge, and returns the current discount ledger without creating a new analysis. Example: call after a referral campaign to inspect earned credits. Use...

No parameters. Call it with no arguments.

iliad_web_researchScrape a single URL with AXIS's owned crawler (SSRF-guarded fetch, robots.txt-aware, readability extraction — no third-party key) and return markdown-formatted content. Honest scope: fetches static HTML only, no JavaScript rendering, so client-rendered SPA pages may extract th...2 params

Scrape a single URL with AXIS's owned crawler (SSRF-guarded fetch, robots.txt-aware, readability extraction — no third-party key) and return markdown-formatted content. Honest scope: fetches static HTML only, no JavaScript rendering, so client-rendered SPA pages may extract th...

Parameters* required
only_main_contentboolean
Extract only the main content (default: true)default: true
url*string
The URL to scrape (http or https)
iliad_web_research_crawlCrawl a domain with AXIS's owned crawler — a same-origin BFS frontier with robots.txt compliance and per-host politeness, no third-party key — and scrape multiple pages. Honest scope: static HTML only, no JavaScript rendering. Returns array of scraped pages with markdown conte...2 params

Crawl a domain with AXIS's owned crawler — a same-origin BFS frontier with robots.txt compliance and per-host politeness, no third-party key — and scrape multiple pages. Honest scope: static HTML only, no JavaScript rendering. Returns array of scraped pages with markdown conte...

Parameters* required
limitnumber
Maximum pages to crawl (1-100, default: 10)default: 10
url*string
The domain/URL to crawl (http or https)
iliad_object_storageAXIS-owned signed-URL minter backed by Cloudflare R2. Returns a pre-signed PUT or GET URL scoped to the calling account (keys are prefixed with `accounts/<account_id>/` server-side, so accounts can't reach each other's objects). Requires Authorization: Bearer <api_key>. Return...8 params

AXIS-owned signed-URL minter backed by Cloudflare R2. Returns a pre-signed PUT or GET URL scoped to the calling account (keys are prefixed with `accounts/<account_id>/` server-side, so accounts can't reach each other's objects). Requires Authorization: Bearer <api_key>. Return...

Parameters* required
content_lengthnumber
Engineer mode (put): pin the EXACT byte size the upload must be (signed; ≤5 GiB). Pairs with content_sha256 for verified content-addressed writes.
content_sha256string
Engineer mode: 64-char hex sha256 of the bytes you'll PUT. When set, the object lands under accounts/<id>/cas/<sha256> so identical content dedupes.
content_typestring
Engineer mode (put): pin the Content-Type the upload must send (signed; R2 rejects a mismatch). Printable ASCII type/subtype, ≤255 chars. Echo via required_headers.
extstring
Engineer mode: optional extension appended to the content-addressed key (e.g. 'png').
key*string
Object key (max 1024 chars), or the prefix for operation=list. Path traversal and leading-/ are rejected.
operation*string
put / get (standard). delete / list / copy and content-addressed put require X-Agent-Mode: engineer (Managed Bucket).one of put · get · delete · list · copy
source_keystring
Engineer mode (operation=copy): source object key to copy from, scoped to your account; `key` is the destination. Echo the returned required_headers on the PUT.
ttl_secondsnumber
Signed-URL lifetime, 1..86400. Defaults to 3600.
iliad_vector_databaseAXIS-owned vector store. Two operations: `upsert` (insert or replace vectors) and `query` (cosine top-k nearest neighbors). Namespaces are account-scoped server-side (`acct:<account_id>:<namespace>`), so tenants cannot read each other's vectors. Persistent across restarts via...6 params

AXIS-owned vector store. Two operations: `upsert` (insert or replace vectors) and `query` (cosine top-k nearest neighbors). Namespaces are account-scoped server-side (`acct:<account_id>:<namespace>`), so tenants cannot read each other's vectors. Persistent across restarts via...

Parameters* required
dedup_thresholdnumber
Engineer upsert: cosine threshold for intra-batch semantic-dedup (default 0.97).
namespacestring
Logical isolation key. Defaults to 'default'. Account ID is always prepended server-side.
operation*string
upsert (insert/replace) or query (top-k cosine).one of upsert · query
queryobject
{vector: number[], top_k?: number, filter?: object}. Engineer mode also reads recency_half_life_days (number — exponential recency decay) and sparse_ids (string[] — RRF hybrid fusion). Required for...
semantic_dedupboolean
Engineer upsert: set false to disable dedup (default on).
vectorsarray
Array of {id, vector, metadata?} — required for upsert.
iliad_embeddingsConvert text into dense vectors. Accepts a single string or a batch (max 2048). Returns one vector per input. AXIS-owned in-process inference by default (node-llama-cpp + an embedding-capable GGUF at AXIS_EMBEDDING_MODEL_PATH — no upstream provider call); an optional OpenAI /v...3 params

Convert text into dense vectors. Accepts a single string or a batch (max 2048). Returns one vector per input. AXIS-owned in-process inference by default (node-llama-cpp + an embedding-capable GGUF at AXIS_EMBEDDING_MODEL_PATH — no upstream provider call); an optional OpenAI /v...

Parameters* required
corpus_adapterboolean
Engineer mode: mean-center the batch (all-but-the-mean) to sharpen retrieval; returns the fitted adapter_mean.
dimensionsnumber
Engineer mode: truncate each vector to this many leading dims (Matryoshka) + renormalize. Smaller, cheaper vectors.
input*string | array
A single string or an array of strings to embed. Empty strings and entries > 32k chars are rejected (chunk before calling).
iliad_transactional_emailSend a single transactional email. Requires Authorization: Bearer <api_key>. Provide either body_html, body_text, or both (Resend will pick the best variant per recipient). All emails ship from RESEND_FROM_ADDRESS — operator must verify that domain in Resend before sending. Re...9 params

Send a single transactional email. Requires Authorization: Bearer <api_key>. Provide either body_html, body_text, or both (Resend will pick the best variant per recipient). All emails ship from RESEND_FROM_ADDRESS — operator must verify that domain in Resend before sending. Re...

Parameters* required
body_htmlstring
HTML body. At least one of body_html / body_text required.
body_textstring
Plaintext body. At least one of body_html / body_text required.
dkim_selectorstring
Engineer mode: DKIM selector (alphanumeric/hyphen, 1-32). Defaults 'axis'.
dmarc_policystring
Engineer mode: DMARC policy none|quarantine|reject. Defaults none (monitoring).
domainstring
Engineer mode (Deliverability): domain to generate SPF/DKIM/DMARC setup for. Replaces the send.
providerstring
Engineer mode: ESP for the SPF include (resend/sendgrid/mailgun/postmark/ses/google). Defaults resend.
reply_tostring
Optional Reply-To address.
subjectstring
Email subject (max 998 chars, RFC 5322).
tostring | array
Recipient address or array of addresses (max 50). Required for a send (standard mode).
iliad_llm_inferenceAXIS-hosted LLM chat-completion via node-llama-cpp + a small GGUF model loaded in-process. Two input shapes accepted: `prompt` (single string) or `messages` (chat-style array of {role, content}). Sampling controls: `max_tokens` (≤2048), `temperature` (0-2), `top_k`, `top_p`, `...10 params

AXIS-hosted LLM chat-completion via node-llama-cpp + a small GGUF model loaded in-process. Two input shapes accepted: `prompt` (single string) or `messages` (chat-style array of {role, content}). Sampling controls: `max_tokens` (≤2048), `temperature` (0-2), `top_k`, `top_p`, `...

Parameters* required
json_schemaobject
Engineer mode (required): a JSON Schema. Decoding is grammar-constrained to it and the output is validated against it; returns a `structured` block.
max_tokensnumber
Max tokens to generate. Defaults 512, hard cap 2048.
messagesarray
Chat-style input. Array of {role: system|user|assistant, content: string}.
promptstring
Single-prompt completion input. Use either this OR messages, not both.
seednumber
Optional seed, threaded through with temperature for more deterministic output. Not a proven byte-identical guarantee (thread count/matmul reduction order isn't pinned) — see the tool description.
stoparray
Stop sequences. Generation halts when any string in the array is produced.
systemstring
Optional system prompt (prompt mode only). For messages mode, use role=system entries.
temperaturenumber
Sampling temperature in [0, 2]. Defaults 0.7.
top_knumber
Top-k sampling (positive integer). Defaults 40.
top_pnumber
Top-p nucleus sampling in (0, 1]. Defaults 0.95.
iliad_code_sandboxAXIS-owned secure code execution. Each call spawns a fresh ephemeral Docker container with hardened isolation: no network, read-only root filesystem, all Linux capabilities dropped, no-new-privileges, PID/memory/CPU limits, tmpfs /tmp only, runs as nobody:nobody. Container is...4 params

AXIS-owned secure code execution. Each call spawns a fresh ephemeral Docker container with hardened isolation: no network, read-only root filesystem, all Linux capabilities dropped, no-new-privileges, PID/memory/CPU limits, tmpfs /tmp only, runs as nobody:nobody. Container is...

Parameters* required
code*string
Source code to execute. Fed via stdin to the interpreter. Max 256 KiB.
language*string
Runtime language.one of python · node · bash
stdinstring
Optional additional stdin appended after the code body. Max 1 MiB.
timeout_secondsnumber
Wall-clock limit. Defaults 30, max 600. SIGKILL on overrun.
iliad_document_parsingAXIS-owned document → Markdown extractor. Accepts either `document_url` (https fetch + 50 MiB cap + 60s timeout) or `document_base64` (inline bytes, 50 MiB decoded cap) — exactly one. Optional `mime_type` hint (application/pdf, application/vnd.openxmlformats-officedocument.wor...4 params

AXIS-owned document → Markdown extractor. Accepts either `document_url` (https fetch + 50 MiB cap + 60s timeout) or `document_base64` (inline bytes, 50 MiB decoded cap) — exactly one. Optional `mime_type` hint (application/pdf, application/vnd.openxmlformats-officedocument.wor...

Parameters* required
document_base64string
Base64-encoded document bytes. Use this OR document_url, not both.
document_urlstring
https URL to a document. Use this OR document_base64, not both.
json_schemaobject
Engineer mode: a JSON Schema. The document is extracted into a validated object matching it (returned in engineer.extracted).
mime_typestring
Optional MIME-type hint. When omitted we sniff from magic bytes + URL extension. Engineer mode: an image/* mime triggers OCR.
iliad_web_searchAXIS-owned BM25 search engine over the corpus YOUR account has indexed. NOT a Google/Bing scraper — agents build their own searchable index by first calling operation='index' with documents (often pages fetched via iliad_web_research), then querying with operation='search'. Fi...8 params

AXIS-owned BM25 search engine over the corpus YOUR account has indexed. NOT a Google/Bing scraper — agents build their own searchable index by first calling operation='index' with documents (often pages fetched via iliad_web_research), then querying with operation='search'. Fi...

Parameters* required
doc_idstring
Document id to remove. Required in delete mode.
documentobject
Single document {doc_id, url?, title?, content, metadata?} — used in index mode (alternative to documents[]).
documentsarray
Batch of documents (max 100). Transactional — malformed entry aborts the whole call.
max_resultsnumber
Cap on hits returned. Defaults 10, max 100.
namespacestring
Logical isolation key. Defaults 'default'. Account id is always prepended server-side.
operation*string
index | search | delete | delete_namespace | count.one of index · search · delete · delete_namespace · count
querystring
Search query (1-1024 chars). Required in search mode.
sitestring
Filter to a single URL host (e.g. 'docs.python.org', case-insensitive).
iliad_text_to_speechAXIS-owned voice synthesis via Piper (rhasspy/piper) + ffmpeg-static. Accepts `text` (1-5000 chars), optional `voice` slug (filename without extension; defaults to AXIS_PIPER_DEFAULT_VOICE or the first available voice), optional `format` (wav | mp3 | opus; defaults wav), optio...7 params

AXIS-owned voice synthesis via Piper (rhasspy/piper) + ffmpeg-static. Accepts `text` (1-5000 chars), optional `voice` slug (filename without extension; defaults to AXIS_PIPER_DEFAULT_VOICE or the first available voice), optional `format` (wav | mp3 | opus; defaults wav), optio...

Parameters* required
brand_textstring
Required when X-Agent-Mode: engineer is set (the call throws without it); ignored otherwise. Brand / voice-and-tone artifact — AXIS derives a voice persona from it and synthesizes in that voice (ov...
formatstring
Audio codec.one of wav · mp3 · opus
genderstring
Engineer mode: persona gender override.one of female · male
localestring
Engineer mode: persona locale override.one of us · gb
sentence_silencenumber
Per-sentence silence in seconds (0-5). Defaults 0.2.
text*string
Text to speak. 1-5000 chars after trim.
voicestring
Voice slug (filename without extension, e.g. 'en_US-amy-medium'). Defaults to first available voice or AXIS_PIPER_DEFAULT_VOICE.
iliad_speech_to_textAXIS-owned audio transcription via whisper.cpp + ffmpeg-static. Accepts either `audio_url` (https URL we fetch, max 100 MiB, 60s download timeout) or `audio_base64` (inline bytes, max 100 MiB decoded) — exactly one. Accepts any audio format ffmpeg can decode (mp3, wav, m4a, op...7 params

AXIS-owned audio transcription via whisper.cpp + ffmpeg-static. Accepts either `audio_url` (https URL we fetch, max 100 MiB, 60s download timeout) or `audio_base64` (inline bytes, max 100 MiB decoded) — exactly one. Accepts any audio format ffmpeg can decode (mp3, wav, m4a, op...

Parameters* required
audio_base64string
Base64-encoded audio bytes. Use this OR audio_url, not both.
audio_urlstring
https URL to an audio file. Use this OR audio_base64, not both.
diarization_gap_secondsnumber
Engineer mode: pause (seconds) between segments that starts a new speaker turn. Defaults 0.75.
initial_promptstring
Optional bias prompt (≤512 chars) — useful for spelling of rare names.
languagestring
ISO-639-1 language code (en, fr, ja, ...) or 'auto' to autodetect. Defaults 'auto'.
max_speakersnumber
Engineer mode: max alternating speaker labels. Defaults 2.
word_timestampsboolean
Emit word-level timestamps within segments. Defaults false.
iliad_analyticsAXIS-owned product analytics. Two operations: `capture` (insert events) and `query` (aggregations). Capture accepts a single `event` or a batch via `events[]` (max 500). Query kinds: `count` (total events), `count_by_event` (top events by frequency), `distinct_users` (unique u...5 params

AXIS-owned product analytics. Two operations: `capture` (insert events) and `query` (aggregations). Capture accepts a single `event` or a batch via `events[]` (max 500). Query kinds: `count` (total events), `count_by_event` (top events by frequency), `distinct_users` (unique u...

Parameters* required
eventobject
Single event payload {event, user_id?, properties?, timestamp?} — used in capture mode.
eventsarray
Batch of event payloads (max 500). Transactional — partial inserts never persist.
namespacestring
Logical isolation key. Defaults to 'default'. Account id is always prepended server-side.
operation*string
capture or query.one of capture · query
queryobject
{kind, event?, from_ts?, to_ts?, property_filter?, bucket?, limit?} — used in query mode.
axis_validateValidate an avatar mesh against 38 rules; returns pass/warn/fail counts. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXI...3 params

Validate an avatar mesh against 38 rules; returns pass/warn/fail counts. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXI...

Parameters* required
file_path*string
Path to mesh file (.glb, .obj, .stl, etc.)
platformstring
Target platform for platform-specific validationone of unity · unreal · godot · roblox · axis_engine
profilestring
Validation strictness profileone of default · strict · lenient
axis_inspectInspect an avatar's contract state and provenance chain. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https...1 params

Inspect an avatar's contract state and provenance chain. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https...

Parameters* required
file_path*string
Path to mesh file (.glb, .obj, .stl, etc.)
axis_compareCompare two avatar contracts; returns similarity score and section-level diffs. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing...3 params

Compare two avatar contracts; returns similarity score and section-level diffs. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing...

Parameters* required
file_a*string
Path to first mesh file
file_b*string
Path to second mesh file
sectionsarray
Limit comparison to specific contract sections
axis_manifest_verifyVerify an export manifest's integrity and optionally check content hash. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXI...2 params

Verify an export manifest's integrity and optionally check content hash. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXI...

Parameters* required
expected_hashstring
Expected content hash for verification
manifest*object
Export manifest JSON object
roblox_compliance_checkRun Roblox R15 compliance checks against a mesh. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https://api.a...1 params

Run Roblox R15 compliance checks against a mesh. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https://api.a...

Parameters* required
file_path*string
Path to mesh file (.glb, .obj, .stl, etc.)
iliad_hygieneAXIS-owned workspace hygiene grader. Analyzes an inline file set [{path,content}] and returns a letter grade (A-F) across a closed set of dimensions plus structured findings. Two modes: mode='scan' (DEFAULT, FREE) returns grade + findings (committed-secret scan, .env/secret-fi...3 params

AXIS-owned workspace hygiene grader. Analyzes an inline file set [{path,content}] and returns a letter grade (A-F) across a closed set of dimensions plus structured findings. Two modes: mode='scan' (DEFAULT, FREE) returns grade + findings (committed-secret scan, .env/secret-fi...

Parameters* required
configobject
Optional threshold overrides: maxFileBytes, coverageA, coverageB, coverageC, todoDebtThreshold.
files*array
Inline files [{path, content}] to scan (non-empty; each content <= 5 MB).
modestring
scan (free grade+findings, default) | fix (metered, adds remediation plan).one of scan · fix
sca_exemption_decisionDecide the lighter-SCA path for a single transaction using AXIS's published 7-priority PSD2 exemption matrix (the same decideScaExemption engine that renders the SCA Exemption Decision Matrix in generated artifacts). Input: amount_eur (required, PSD2 thresholds are EUR-denomin...8 params

Decide the lighter-SCA path for a single transaction using AXIS's published 7-priority PSD2 exemption matrix (the same decideScaExemption engine that renders the SCA Exemption Decision Matrix in generated artifacts). Input: amount_eur (required, PSD2 thresholds are EUR-denomin...

Parameters* required
amount_eur*number
Transaction amount in EUR (PSD2 thresholds are EUR-denominated).
has_prior_scaboolean
A prior SCA exists — gates recurring_fixed and trusted_beneficiary.
is_merchant_initiatedboolean
MIT with stored credential + original SCA reference (out of SCA scope).
is_one_leg_outboolean
Payer or payee outside the EEA (territorial scope, not a formal exemption).
is_recurring_fixedboolean
Fixed-amount subsequent collection (RTS Art. 13). Requires has_prior_sca.
is_secure_corporateboolean
Dedicated/lodged corporate card program (RTS Art. 16).
is_trusted_beneficiaryboolean
Merchant on the cardholder's trusted list (RTS Art. 12). Requires has_prior_sca.
tra_acquirer_fraud_bpsnumber
Acquirer reference fraud rate in basis points (EBA RTS Art. 15 bands: <=1 → €500 cap, <=6 → €250, <=13 → €100).
grade_complianceRun the real 8-check AP2/Visa compliance grading engine (gradeCompliance — the same engine behind computeComplianceGrade and the commerce registry's verified_decisions block) over an inline file set. Each of the 8 validators (SCA/3DS2 readiness, AP2 mandate validity, tokenizat...1 params

Run the real 8-check AP2/Visa compliance grading engine (gradeCompliance — the same engine behind computeComplianceGrade and the commerce registry's verified_decisions block) over an inline file set. Each of the 8 validators (SCA/3DS2 readiness, AP2 mandate validity, tokenizat...

Parameters* required
files*array
Source files to grade (max 25 files, 50KB each, 1MB total)
assemble_ce3_evidenceAssemble a Visa Compelling Evidence 3.0 packet + eligibility verdict for a disputed card-absent-fraud (reason code 10.4) transaction using the real assembleCe3 engine: finds prior undisputed transactions in the caller-supplied history that share >=2 qualified data elements (de...2 params

Assemble a Visa Compelling Evidence 3.0 packet + eligibility verdict for a disputed card-absent-fraud (reason code 10.4) transaction using the real assembleCe3 engine: finds prior undisputed transactions in the caller-supplied history that share >=2 qualified data elements (de...

Parameters* required
dispute*object
{txn: {id, amount_minor, currency, created_at, disputed, device_id?, ip_address?, email?, shipping_address?, login_id?}, reason_code: string (CE 3.0 requires '10.4'), disputed_at: ISO timestamp}
transaction_historyarray
Candidate prior transactions (same Txn shape, max 500). Undisputed priors sharing >=2 qualified elements qualify.
build_ap2_mandateValidate, canonically encode, and optionally Ed25519-sign an AP2 mandate (Intent / Cart / Payment) using the real @axis/ap2 codecs — schema validation (including cart-total arithmetic and intent cross-references), RFC 8785 JCS-style canonical JSON encoding, and detached-JWS Ed...3 params

Validate, canonically encode, and optionally Ed25519-sign an AP2 mandate (Intent / Cart / Payment) using the real @axis/ap2 codecs — schema validation (including cart-total arithmetic and intent cross-references), RFC 8785 JCS-style canonical JSON encoding, and detached-JWS Ed...

Parameters* required
intent_contextobject
Optional IntentMandate to cross-reference a cart's intent_ref against.
mandate*object
An AP2 mandate object: {kind: 'intent'|'cart'|'payment', version: 'ap2/1', id, created_at, ...kind-specific fields (intent: user_id/description/constraints.max_amount/expires_at; cart: intent_ref/m...
seed_hexstring
Optional 64-char hex (32-byte) Ed25519 seed to sign with. Caller-supplied key material — AXIS stores no keys. Omit for an unsigned template.
score_dispute_readinessScore how ready a disputed transaction's EVIDENCE FILE is for representment, per Visa reason-code family, using the transparent scoreWinProbability heuristic (win-prob-v0: hand-set, documented logistic coefficients — exported, inspectable, monotonic in evidence). Input: reason...2 params

Score how ready a disputed transaction's EVIDENCE FILE is for representment, per Visa reason-code family, using the transparent scoreWinProbability heuristic (win-prob-v0: hand-set, documented logistic coefficients — exported, inspectable, monotonic in evidence). Input: reason...

Parameters* required
evidenceobject
Evidence on file: {ce3Eligible?, matchingDataElements? (0-5), priorUndisputedTransactions? (0-10), hasDeliveryProof?, hasAvsMatch?, hasCvvMatch?, has3dsAuthenticated?, hasSignedMandate?, hasCustome...
reason_code*string
Visa dispute reason code (e.g. '10.4', '13.1', '12.5'). Unknown codes fall back to a documented default family.
assemble_representmentTurn a webhook-ingested dispute (charge.dispute.* events persist DisputeRecords server-side) into a Stripe representment: qualifies CE 3.0 priors from your supplied transaction history (assembleCe3), builds the Stripe `evidence` hash (buildStripeRepresentment), walks the dispu...5 params

Turn a webhook-ingested dispute (charge.dispute.* events persist DisputeRecords server-side) into a Stripe representment: qualifies CE 3.0 priors from your supplied transaction history (assembleCe3), builds the Stripe `evidence` hash (buildStripeRepresentment), walks the dispu...

Parameters* required
dispute_id*string
Provider dispute id (Stripe dp_...) previously ingested by the charge.dispute.created webhook.
disputed_txnobject
Optional CE 3.0 data elements of the disputed transaction: {device_id?, ip_address?, email?, shipping_address?, login_id?}.
evidence_inputsobject
{customerEmail?, shippingAddress?, billingAddress?, serviceDate?, productDescription?, deliveryTracking?, threeDsAuthenticated?} — merchant-supplied evidence fields.
submitboolean
true → submit the built evidence to the Stripe disputes API (requires STRIPE_SECRET_KEY server-side). Default false (assemble only).
transaction_historyarray
Candidate prior transactions for CE 3.0 qualification (Txn shape, max 500).
iliad_network_tokenizationNetwork-tokenization capability. (1) `lifecycle`: an EXECUTABLE TAP-style token-lifecycle state machine (provision → activate → suspend → resume → delete; deleted is terminal; illegal transitions are rejected with an error, not silently accepted) — pure simulation, no real pay...6 params

Network-tokenization capability. (1) `lifecycle`: an EXECUTABLE TAP-style token-lifecycle state machine (provision → activate → suspend → resume → delete; deleted is terminal; illegal transitions are rejected with an error, not silently accepted) — pure simulation, no real pay...

Parameters* required
eventstring
lifecycle: single-event shorthand for `events: [event]`.
eventsarray
lifecycle: ordered TokenEvent list (provision|activate|suspend|resume|delete), max 100. Must start from provision; illegal transitions throw.
operationstring
read (default, disabled) | provision (disabled) | lifecycle | capabilities.one of read · provision · lifecycle · capabilities
pan_sourcestring
provision: ignored — this operation is disabled and always returns _not_configured. NEVER a raw PAN in any case.
payment_method_idstring
read: ignored — this operation is disabled and always returns _not_configured.
providerstring
provision: ignored — this operation is disabled and always returns _not_configured.one of stripe · vts · mdes

Sponsors

Readme

Axis' Iliad

Axis' Iliad — The modern epic that shapes raw codebases into canonical, agent-ready artifacts. Axis' Iliad authors the definitive foundation for the next era of natural-language workspace development.

Canonical name: Axis' Iliad. Use this name consistently across docs, registries, and integrations.

Tests Coverage Website API Version License AXIS-iliad MCP server


AXIS Ecosystem


View the full README on GitHub

Details

Repository
github.com/lastmanupinc-hub/axis-iliad
Website
api.iliad.trustfabric.ai/for-agents
Transport
HTTP
Auth
Required
Registry
MCP registry, active
Tools verified
Nov 6, 2026