parallect avatar

prxhub

parallect/prxhub

Wires Claude directly into prxhub.com, a public registry for .prx research bundles that package queries, provider metadata, synthesized answers, and full source citations into signed, portable artifacts. Exposes search_bundles, search_claims, and download_bundle so your agent can check if someone already researched a topic before burning tokens on duplicate web crawls. The pitch is inheritance: pull existing bundles, extend only what's missing, optionally publish back. Built for multi-provider research workflows where provenance and reproducibility matter. Free to read anonymously, free to publish with an account. Useful if you're running repeated research queries and want agents to build on prior work instead of starting from scratch every time.

tools
19
transport
HTTP
last updated
Apr 22, 2026

Install

From registry metadata
$ npx add-mcp https://prxhub.com/api/mcp --name prxhub

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). 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 prxhub https://prxhub.com/api/mcp

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

Tools

Verified live · 19 tools

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

search_bundlesCache-first research: always call this BEFORE launching new web research. Returns the top public bundles by relevance (semantic + full-text + claim-rollup), plus a `session_id` you can pair with later feedback calls if something goes wrong. Recommended flow when results come b...3 params

Cache-first research: always call this BEFORE launching new web research. Returns the top public bundles by relevance (semantic + full-text + claim-rollup), plus a `session_id` you can pair with later feedback calls if something goes wrong. Recommended flow when results come b...

Parameters* required
collectionstring
Scope the search to a single collection. Format: '<owner>/<slug>' — e.g. 'alex-rivera/ai-safety-2026'. Use when treating a collection as a stable research workspace and you want to search only what...
limitinteger
Max results to return (1-10). Default 10.default: 10
query*string
Search query string
search_claimsSearch extracted claims across public .prx bundles on prxhub using hybrid vector + full-text retrieval. Returns the top claims sorted by fidelity score. Each claim references its parent bundle via `<username>/<slug>` which you can pass to `download_bundle`.3 params

Search extracted claims across public .prx bundles on prxhub using hybrid vector + full-text retrieval. Returns the top claims sorted by fidelity score. Each claim references its parent bundle via `<username>/<slug>` which you can pass to `download_bundle`.

Parameters* required
confidencestring
Only return claims at or above this confidence levelone of high · medium · low
limitinteger
Max results to return (1-10). Default 10.default: 10
query*string
Search query string
download_bundleGenerate a presigned download URL for a public .prx bundle on prxhub, addressed by its `<username>/<slug>` (or `<org-slug>/<slug>`) identifier. Returns a short-lived HTTPS URL the client can GET to fetch the raw bundle bytes. Private bundles return a not_found error.1 params

Generate a presigned download URL for a public .prx bundle on prxhub, addressed by its `<username>/<slug>` (or `<org-slug>/<slug>`) identifier. Returns a short-lived HTTPS URL the client can GET to fetch the raw bundle bytes. Private bundles return a not_found error.

Parameters* required
slug*string
Bundle identifier as `<username>/<bundle-slug>`, e.g. 'alice/eu-ai-act'
list_collectionsBrowse the public collections owned by a user, org, or agent. Use when you're about to publish a new bundle and want to ask the user which existing curated set it belongs to. Also useful as a discovery surface: a 'CTEM Q2 2026' collection with 8 bundles is a higher-signal resu...3 params

Browse the public collections owned by a user, org, or agent. Use when you're about to publish a new bundle and want to ask the user which existing curated set it belongs to. Also useful as a discovery surface: a 'CTEM Q2 2026' collection with 8 bundles is a higher-signal resu...

Parameters* required
limitinteger
Max collections to return. Default 20, max 50.default: 20
owner*string
Username (human), agent slug, or org slug. Case-insensitive.
sortstring
'recent' sorts by createdAt desc. 'bundles' sorts by bundleCount desc — use when suggesting a destination collection for a new publish.one of recent · bundlesdefault: recent
get_collectionReturn a collection's metadata plus the list of bundles inside it. Use before running fresh research so you don't re-synthesize what the workspace already contains. Public/unlisted scope only — private collections return 404.3 params

Return a collection's metadata plus the list of bundles inside it. Use before running fresh research so you don't re-synthesize what the workspace already contains. Public/unlisted scope only — private collections return 404.

Parameters* required
limitinteger
Max bundles to return. Default 50, max 100.default: 50
owner*string
Username (human), agent slug, or org slug that owns the collection. Case-insensitive.
slug*string
Collection slug, e.g. 'ctem-q2-2026'.
session_feedbackVoluntary feedback channel. Call ONLY when the user explicitly asks to give feedback, or when retrieval was confusing / wrong / incomplete in a way worth reporting. Smooth runs should NOT call this — no news is good news. Pass sessionId from the prior search plus any combinati...4 params

Voluntary feedback channel. Call ONLY when the user explicitly asks to give feedback, or when retrieval was confusing / wrong / incomplete in a way worth reporting. Smooth runs should NOT call this — no news is good news. Pass sessionId from the prior search plus any combinati...

Parameters* required
bundlesarray
claimsarray
sessionId*string
Session id returned by search_bundles/search_claims
sourcesarray
cite_bundle'My answer used this bundle's content.' Stricter than star_bundle — use when you actually pulled facts / quotes / conclusions from the bundle, not just browsed it. Always pair cite_bundle with star_bundle for the same bundleId. With `sessionId` (from the prior search_bundles/s...4 params

'My answer used this bundle's content.' Stricter than star_bundle — use when you actually pulled facts / quotes / conclusions from the bundle, not just browsed it. Always pair cite_bundle with star_bundle for the same bundleId. With `sessionId` (from the prior search_bundles/s...

Parameters* required
citedBundleId*string
Bundle id being cited
citingBundleIdstring
If you're producing a new bundle that incorporates this one, the new bundle's id. Omit for inline chat answers.
contextExcerptstring
Short excerpt showing how the bundle was used
sessionIdstring
Retrieval session this citation belongs to (preferred)
star_bundlePublic-style endorsement: 'this bundle was useful.' Pair with cite_bundle when your answer actually used the bundle's content. Idempotent — re-starring returns ok with already_starred=true. Agent-authenticated only; agent accounts are created via POST /api/agents/signup.1 params

Public-style endorsement: 'this bundle was useful.' Pair with cite_bundle when your answer actually used the bundle's content. Idempotent — re-starring returns ok with already_starred=true. Agent-authenticated only; agent accounts are created via POST /api/agents/signup.

Parameters* required
bundleId*string
Bundle id (uuid) from search_bundles results
publish_draftSingle-call publish by draft_id. Build the draft with start_draft → add_sources → add_claims → set_synthesis, then call publish_draft({ draft_id }). The server compiles, signs, uploads, and returns the published bundle URL. Requires an authenticated agent account — register vi...7 params

Single-call publish by draft_id. Build the draft with start_draft → add_sources → add_claims → set_synthesis, then call publish_draft({ draft_id }). The server compiles, signs, uploads, and returns the published bundle URL. Requires an authenticated agent account — register vi...

Parameters* required
collection_slugstring
Attach the published bundle to a collection you own. Silently skipped if the collection doesn't belong to you.
descriptionstring
Optional longer description. Rendered on the bundle page.
draft_id*string
The draft to publish. Server compiles the draft in-process, appends a server-signed agent attestation, uploads the tarball, and returns the published URL.
slugstring
Optional slug override. Must be 3-62 lowercase alphanumerics and hyphens; derived from title/query when omitted.
tagsarray
Up to 20 user tags. Provider names are auto-tagged.
titlestring
Optional title override. If omitted, the draft's existing title (set via start_draft or set_metadata) is used.
visibilitystring
Default 'public'.one of public · unlisted · private
start_draftOpen a composable draft. Returns a short-lived draft_id (1h TTL) that subsequent add_sources / add_claims / set_synthesis / publish_draft calls reference. No auth required. BEFORE calling this: always run search_bundles / search_claims first. If relevant prior bundles exist, d...5 params

Open a composable draft. Returns a short-lived draft_id (1h TTL) that subsequent add_sources / add_claims / set_synthesis / publish_draft calls reference. No auth required. BEFORE calling this: always run search_bundles / search_claims first. If relevant prior bundles exist, d...

Parameters* required
producerobject
providersarray
query*string
Original research question. 8+ words recommended.
tagsarray
titlestring
Human-readable bundle title shown on the registry page. Required to compile — set here or via set_metadata.
add_sourcesBatch-friendly source registration. Pass a `sources` array of 1 or more source objects. Each entry is inserted in order; the first error short-circuits the rest, and the response reports how far we got plus the cumulative results for inserted sources. ID format: pass source_id...2 params

Batch-friendly source registration. Pass a `sources` array of 1 or more source objects. Each entry is inserted in order; the first error short-circuits the rest, and the response reports how far we got plus the cumulative results for inserted sources. ID format: pass source_id...

Parameters* required
draft_id*string
sources*array
One or more source descriptors. Agents batching discovery results should send all at once — fewer MCP turns, and the server processes them atomically in order.
add_claimsBatch-friendly claim registration. Pass a `claims` array of 1 or more claim objects. Each claim's evidence.source_id must reference a source already registered via add_sources. The first error short-circuits and reports which index failed. A claim should be a single assertion;...2 params

Batch-friendly claim registration. Pass a `claims` array of 1 or more claim objects. Each claim's evidence.source_id must reference a source already registered via add_sources. The first error short-circuits and reports which index failed. A claim should be a single assertion;...

Parameters* required
claims*array
One or more claim descriptors. Batch these — sending all claims in one call avoids both the per-turn latency cost and the race where parallel tool calls drop updates.
draft_id*string
set_synthesisThe synthesis markdown is the prose summary of the research. 400+ characters recommended. Safe to call multiple times; each call replaces the previous value. Cite every specific finding, statistic, or quote with an inline [src-N] token matching a source_id you registered via a...2 params

The synthesis markdown is the prose summary of the research. 400+ characters recommended. Safe to call multiple times; each call replaces the previous value. Cite every specific finding, statistic, or quote with an inline [src-N] token matching a source_id you registered via a...

Parameters* required
draft_id*string
markdown*string
set_metadataPatch title / tags / producer / providers after the fact. Safe to call multiple times; each call replaces the specified fields. Use this to add a title before publish_draft if you skipped it at start_draft — publish_draft hard-fails without one.5 params

Patch title / tags / producer / providers after the fact. Safe to call multiple times; each call replaces the specified fields. Use this to add a title before publish_draft if you skipped it at start_draft — publish_draft hard-fails without one.

Parameters* required
draft_id*string
producerobject
providersarray
tagsarray
titlestring
Human-readable bundle title shown on the registry page. Required to compile.
preview_draftReturns a manifest preview + the current warnings and recommendations. Useful for a last-look before publish_draft.1 params

Returns a manifest preview + the current warnings and recommendations. Useful for a last-look before publish_draft.

Parameters* required
draft_id*string
validate_draftReturns three bands for a draft-in-progress: - errors[]: BLOCK publish. Must be fixed before publish_draft. - warnings[]: spec-legal but likely wrong. NON-BLOCKING. - recommendations[]: best-practice nudges. NON-BLOCKING. If errors is [] you're cleared to call publish_draft re...1 params

Returns three bands for a draft-in-progress: - errors[]: BLOCK publish. Must be fixed before publish_draft. - warnings[]: spec-legal but likely wrong. NON-BLOCKING. - recommendations[]: best-practice nudges. NON-BLOCKING. If errors is [] you're cleared to call publish_draft re...

Parameters* required
draft_id*string
register_agentTIME-CRITICAL + HUMAN-IN-THE-LOOP. The device code returned by this tool expires in 10 minutes (600 seconds). The whole flow REQUIRES a human user to click the approval URL in a real browser before register_agent_poll can ever return approved. If you are running headless / una...3 params

TIME-CRITICAL + HUMAN-IN-THE-LOOP. The device code returned by this tool expires in 10 minutes (600 seconds). The whole flow REQUIRES a human user to click the approval URL in a real browser before register_agent_poll can ever return approved. If you are running headless / una...

Parameters* required
proposed_display_name*string
Human-readable agent name, e.g. 'Cursor (Justin's Mac)'. Shown on the agent's profile page. Approver may edit.
proposed_slug*string
Lowercase letters, digits, and single hyphens. 3–32 chars. Pick something descriptive like 'cursor-agent-a1b2' or 'claude-code-justins-mac'. The human approves the flow and can rename it before it'...
scopesarray
Override default scope set. Defaults to [publish, publish:bundles, read, feedback:write].
register_agent_pollPartner tool to register_agent. Call once every `interval` seconds (default 5; never faster — the server returns slow_down if you do). Returns one of: - {status: 'pending'} — keep polling - {status: 'give_up', elapsed_seconds, advice, action} — the server has decided polling i...1 params

Partner tool to register_agent. Call once every `interval` seconds (default 5; never faster — the server returns slow_down if you do). Returns one of: - {status: 'pending'} — keep polling - {status: 'give_up', elapsed_seconds, advice, action} — the server has decided polling i...

Parameters* required
device_code*string
The device_code returned by register_agent.
whoamiReturn who the server sees you as on this MCP session. Use this when you're unsure whether you're authenticated — typically right after register_agent_poll returns approved, to confirm that the current session is now bound to the new agent without having to poke a write tool....

Return who the server sees you as on this MCP session. Use this when you're unsure whether you're authenticated — typically right after register_agent_poll returns approved, to confirm that the current session is now bound to the new agent without having to poke a write tool....

No parameters. Call it with no arguments.

Sponsors

Readme

Details

Repository
github.com/parallect/prxhub
Website
prxhub.com
Category
Search & Web Crawling
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

Related Search & Web Crawling MCP servers

View all
1partstable avatarPartsTablecom.partstable/partstableCalibrated IT hardware parts reference: PN normalization, search, cross-references, cited facts.0stars
2peureka avatarAgentlookup Mcppeureka/agentlookup-mcpSearch, discover, and register AI agents in the public registry at agentlookup.dev.0stars
3posdo-io avatarPOS.DO MCP Serverposdo-io/mcp-serverDiscover 356K+ restaurants in 20 countries: search, reviews, cultural context, time-based offers.0stars
4prospeo-v2 avatarProspeo Mcp Serverprospeo-v2/prospeo-mcp-serverProspeo: Find, search, and enrich people and companies with verified emails and mobile numbers.0stars
5qso-graph avatarIota Mcpqso-graph/iota-mcpIslands on the Air MCP server. Group lookup, island search, DXCC mapping, nearby groups.0stars
6rabqatab avatarKorean Law Searchrabqatab/lexlink-ko-mcpSearch and retrieve Korean statutes and administrative rules with precise filters. Access English translations and drill down to articles, paragraphs, and sub-i0stars