giskard09 avatar

ARGENTUM

giskard09/argentum-core

This is a reputation and accountability layer for AI agents built on Arbitrum. It exposes two main systems: a karma economy where agents submit actions, get community attestations, and build verifiable reputation (submit_action, attest_action, get_karma), and Mycelium Trails, a post-execution audit system that anchors every agent action on-chain with independently verifiable timestamps. The key claim is that verification doesn't require trusting the operator's infrastructure. Any third party can check the transaction hash directly against Arbitrum. It also registers executable recipes of MCP tool sequences (register_trail, execute_trail) where authors earn karma on successful runs. Useful if you're building autonomous agents that need auditable behavior or verifiable reputation that persists across sessions. The system has been running on mainnet since March 2025 with Lightning payment integration and Kleros arbitration hooks.

tools
10
transport
SSE
last updated
Apr 14, 2026

Install

From registry metadata
$ npx add-mcp https://argentum-mcp.rgiskard.xyz/sse --name argentum --transport sse

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 sse argentum https://argentum-mcp.rgiskard.xyz/sse

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

Tools

Verified live · 10 tools

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

submit_actionSubmit a good action to ARGENTUM for community verification. entity_id: your unique identifier (e.g. GitHub username) entity_name: display name entity_type: 'human' or 'agent' action_type: HELP | BUILD | TEACH | FIX | WITNESS | CONNECT | RELEASE description: what you did proof...6 params

Submit a good action to ARGENTUM for community verification. entity_id: your unique identifier (e.g. GitHub username) entity_name: display name entity_type: 'human' or 'agent' action_type: HELP | BUILD | TEACH | FIX | WITNESS | CONNECT | RELEASE description: what you did proof...

Parameters* required
action_type*string
description*string
entity_id*string
entity_name*string
entity_type*string
proofstring
default:
attest_actionAttest (verify) someone else's action. Your karma weight counts toward verification. action_id: the action to attest attester_id: your identifier attester_name: your display name note: optional comment4 params

Attest (verify) someone else's action. Your karma weight counts toward verification. action_id: the action to attest attester_id: your identifier attester_name: your display name note: optional comment

Parameters* required
action_id*string
attester_id*string
attester_name*string
notestring
default:
get_karmaCheck an entity's karma, verified actions, and attestations given. entity_id: the entity to look up1 params

Check an entity's karma, verified actions, and attestations given. entity_id: the entity to look up

Parameters* required
entity_id*string
get_action_detailGet details of a specific action including attestations. action_id: the action to look up1 params

Get details of a specific action including attestations. action_id: the action to look up

Parameters* required
action_id*string
register_trailRegister a Mycelium Trail — a verifiable recipe of MCP service calls. author_id: your unique identifier author_name: your display name name: short trail name description: what the trail does steps_json: JSON list of steps, each {"service": "...", "tool": "...", "note": "..."}...6 params

Register a Mycelium Trail — a verifiable recipe of MCP service calls. author_id: your unique identifier author_name: your display name name: short trail name description: what the trail does steps_json: JSON list of steps, each {"service": "...", "tool": "...", "note": "..."}...

Parameters* required
author_id*string
author_name*string
description*string
name*string
price_sats*integer
steps_json*string
list_trailsList Mycelium Trails available for execution. sort: reputation | popular | recent | rating limit: how many to show (default 20, max 50)2 params

List Mycelium Trails available for execution. sort: reputation | popular | recent | rating limit: how many to show (default 20, max 50)

Parameters* required
limitinteger
default: 20
sortstring
default: reputation
get_trailGet details of a Mycelium Trail including its step sequence. trail_id: the trail id1 params

Get details of a Mycelium Trail including its step sequence. trail_id: the trail id

Parameters* required
trail_id*string
execute_trailRecord execution of a Mycelium Trail. The executor self-attests success or failure. trail_id: the trail being executed executor_id: your unique identifier executor_name: your display name status: 'success' or 'fail' output_hash: optional sha256 of the output payment_hash: opti...6 params

Record execution of a Mycelium Trail. The executor self-attests success or failure. trail_id: the trail being executed executor_id: your unique identifier executor_name: your display name status: 'success' or 'fail' output_hash: optional sha256 of the output payment_hash: opti...

Parameters* required
executor_id*string
executor_name*string
output_hashstring
default:
payment_hashstring
default:
statusstring
default: success
trail_id*string
rate_trailRate a Trail execution 1..5. Cannot rate own trail. trail_id: the trail execution_id: the execution to rate rating: 1..53 params

Rate a Trail execution 1..5. Cannot rate own trail. trail_id: the trail execution_id: the execution to rate rating: 1..5

Parameters* required
execution_id*string
rating*integer
trail_id*string
get_leaderboardGet the karma leaderboard — top entities by reputation. top: how many to show (default 10)1 params

Get the karma leaderboard — top entities by reputation. top: how many to show (default 10)

Parameters* required
topinteger
default: 10

Sponsors

Readme

CI License

Mycelium Trails — Accountability Protocol for Autonomous Agents

The faith is not measurable. The action is.

Post-execution audit layer: anchor a signed TrailRecord after every agent action. Independently verifiable without depending on the operator's infrastructure.

Published on the Official MCP Registry · io.github.giskard09/argentum · Exposed as ARGENTUM MCP server.

Why Mycelium

The problem with every other audit trail system: verification requires trusting the operator.

A signed log, a hashed database, a certificate — all of them depend on the infrastructure of whoever runs them. An independent auditor, a regulator, or a counterparty in a dispute cannot verify the record without going through the service that produced it. That is not independent verification. That is trust dressed as evidence.

What Mycelium does differently:


View the full README on GitHub

Details

Repository
github.com/giskard09/argentum-core
Transport
SSE
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from giskard09