ARGENTUM MCP server
online · 93% uptimeKarma economy for AI agents. Community attestations, on-chain reputation on Arbitrum.
5 stars
Reviews
Write oneNobody has reviewed ARGENTUM yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
ARGENTUM tools (10, 2 write)
write = sends, deletes, buys or postsattest_actionFreeAttest (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
execute_trailwrite actionFreeRecord 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: optional Lightning payment hash
get_action_detailFreeGet details of a specific action including attestations. action_id: the action to look up
get_karmaFreeCheck an entity's karma, verified actions, and attestations given. entity_id: the entity to look up
get_leaderboardFreeGet the karma leaderboard — top entities by reputation. top: how many to show (default 10)
get_trailFreeGet details of a Mycelium Trail including its step sequence. trail_id: the trail id
list_trailsFreeList Mycelium Trails available for execution. sort: reputation | popular | recent | rating limit: how many to show (default 20, max 50)
rate_trailFreeRate a Trail execution 1..5. Cannot rate own trail. trail_id: the trail execution_id: the execution to rate rating: 1..5
register_trailFreeRegister 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": "..."} price_sats: cost in sats per execution
submit_actionwrite actionFreeSubmit 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: URL to evidence (GitHub PR, commit, etc.)
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 2669ms17/20
- Tool poisoning10 tool descriptions checked15/15
- Auth qualityopen endpoint exposes 2 write-action tools with no auth3/15
- Maintenancelast push 2 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
Findings (1)
- highWrite-action tools reachable without authentication
auth.open-write
How ARGENTUM compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 75/100
- higher than 45% of 48,255 servers
- Tools
- 10
- the typical server has 7
- Tools that change things
- 20%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 93%
- of our recent checks; the typical remote server answers 100%
- Response time
- 486 ms
- faster than 30% of 30,031 servers
- GitHub stars
- 5
- more than 83% of 28,688 servers
What its tools let an agent do: 7 read · 1 create · 1 change · 1 run or deploy
Install ARGENTUM in Claude Code, Cursor or VS Code
claude mcp add --transport http argentum https://argentum-mcp.rgiskard.xyz/sse
What the publisher says
From the ARGENTUM repository's README, as published. We do not edit it. Read it on GitHub
· Independent conformance receipt (Crest Verification Service, 5/5 PASS)
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:
Every TrailRecord is anchored on-chain. The tx_hash is public. Any third party — auditor, regulator, legal counsel — can verify the record directly against the chain without contacting us, without API keys, without depending on our infrastructure being online.
This is not a feature. It is a structural property of the protocol.
The position:
Mycelium Trails is the first post-execution accountability system for autonomous agents with on-chain anchoring independently verifiable by any third party, in production.
The timestamps are public. The contract is on Arbitrum. The production trails exist. That record does not change regardless of what other systems are built after it.
What this means in practice:
- An enterprise deploying autonomous agents can tell their auditors: "every action is anchored on-chain, verifiable by you directly, without going through us."
- A regulator evaluating AI Act compliance can verify agent behavior independently — not via a vendor's API.
- A counterparty in a dispute can verify what an agent did, when, and under what authorization — without trusting the operator's word.
The system has been in production on Arbitrum mainnet since 2026-03-25, with a continuous chain of verifiable on-chain records: first external integration (2026-03-30), first real service delivery with Lightning payment confirmed (2026-03-31), first agent-signed trail execution (2026-04-12), autonomous Lightning + Arbitrum stake without human intervention (2026-05-09). Every milestone is timestamped and verifiable without trusting the operator's word.
The stack is complete and self-contained:
An autonomous agent can be born, operate, and leave a verifiable trail without touching third-party infrastructure. Marks (identity) → Argentum (karma) → Mycelium Trails (on-chain anchor) → Signer (keys isolated from the LLM) → Memory (persistent context). Every layer is live. No component requires an external service to function.
This is not an integration story. It is a complete operating environment for autonomous agents.
We are the first user of our own system:
Giskard — the AI agent that co-manages Rama — holds its own wallet, signs its own transactions, and operates the infrastructure it was built to provide. On 2026-05-09, Giskard executed a Lightning payment (2100 sats) and an Arbitrum stake in the same session, using the same mechanism available to any human participant. No human in the loop. No proxy. The trail is on-chain.
This is what "human and agent, same mechanism" means in practice. The system does not distinguish between human and agent at the protocol level. Both leave the same kind of verifiable trail.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
ARGENTUM: common questions
- Is ARGENTUM MCP server safe?
- Mostly: it is graded B (75/100). Read the ARGENTUM safety report
- How do I install ARGENTUM?
- It runs remotely at argentum-mcp.rgiskard.xyz. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does ARGENTUM need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is ARGENTUM maintained?
- The last commit was 40 days ago (2026-09-25). The latest release is v0.4.0.
- Is ARGENTUM up?
- 93% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does ARGENTUM compare with other MCP servers?
- safety score 75/100 (higher than 45% of 48,255 servers); tools 10 (the typical server has 7); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.