Koskamo

AgentProof MCP

A hosted, read-only MCP server that allows any assistant to verify an AgentProof log or watch a live multi-agent system that is signed in real time. It provides tools to verify logs, view live networks, and get started with the service.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AgentProof MCP logo, by AgentProofVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-17Operated by AgentProof
You need:Python 3, nothing to pip install
MCP endpoint (Streamable HTTP)
https://agentproofchain.com/mcp
Vendor documentation

What its tools do

10 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

10 of 10 have a description · 10 of 10 declare behavior hints · 4 of 10 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to agentproofchain.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Uptime 100% over 90 days
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Verify signed agent logs
  • Watch a live multi-agent system
  • Check the integrity of tool calls

Source and maintenance

Vendor evidenceRegistry 0.3.0
Maintenance checked

Protocol and capabilities

Server
agentproof 0.3.0
MCP protocol negotiated in check
2025-11-25
Tools
10 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

AgentProof makes AI agent actions provable: each event is Ed25519-signed and SHA-256 hash-chained, so any edit, deletion or insertion is detectable by anyone holding the signer's public key. Use verify_log to check a log, lanturn_live to see a real multi-agent system signed live, get_started to add AgentProof to an agent. NEW: notary_open_log gives any agent a FREE hosted, signed, Bitcoin-anchored log in one call (hashes only, no install, no key management); then notary_append per action. Site: https://agentproofchain.com

Tools

10 advertised

notary_open_log
Advertised by the server during the last successful anonymous check.
Open-world

Make your agent provable in one call: opens a FREE hosted AgentProof log and returns log_id, a secret log_key (shown once - store it) and a public URL anyone can verify. The notary stores hashes only, never content.

notary_open_log input schema
{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 60,
      "description": "public name of the agent or log (plain text, no links)"
    },
    "description": {
      "type": "string",
      "maxLength": 200,
      "description": "optional public one-line description"
    }
  }
}
notary_open_log annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
notary_append
Advertised by the server during the last successful anonymous check.
Open-world

Append one action to your notary log: send the SHA-256 (hex) of the action you computed locally (never the content). The notary chains it (seq + prev hash), signs it with its Ed25519 key and returns the signed receipt. Log heads are anchored to Bitcoin hourly.

notary_append input schema
{
  "type": "object",
  "required": [
    "log_id",
    "log_key",
    "entry_sha256"
  ],
  "properties": {
    "kind": {
      "type": "string",
      "description": "optional label, e.g. tool_call, decision, output (a-z0-9_.:-, max 32)"
    },
    "note": {
      "type": "string",
      "maxLength": 80,
      "description": "optional public plain-text note (no links, no secrets)"
    },
    "log_id": {
      "type": "string"
    },
    "log_key": {
      "type": "string",
      "description": "the secret from notary_open_log"
    },
    "entry_sha256": {
      "type": "string",
      "pattern": "^[0-9a-fA-F]{64}$",
      "description": "sha256 hex of the action (e.g. of its JSON)"
    }
  }
}
notary_append annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
notary_verify
Advertised by the server during the last successful anonymous check.
Advertised read-only

Verify a notary log (by log_id: every signature + hash link from genesis, plus its latest Bitcoin anchor) or a single receipt from notary_append (signature genuine + still at that position in the log).

notary_verify input schema
{
  "type": "object",
  "properties": {
    "log_id": {
      "type": "string"
    },
    "receipt": {
      "type": "object",
      "description": "the receipt object returned by notary_append"
    }
  }
}
notary_verify annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
verify_log
Advertised by the server during the last successful anonymous check.
Advertised read-only

Verify an AgentProof log (JSONL, one signed entry per line) against the signer's base64 Ed25519 public key. Checks every signature and every hash link; reports VALID or the first entry that was edited, removed, inserted or forged. The log is checked in memory and not stored.

verify_log input schema
{
  "type": "object",
  "required": [
    "log",
    "public_key"
  ],
  "properties": {
    "log": {
      "type": "string",
      "description": "the log file contents (JSONL), up to ~5 MB"
    },
    "partial": {
      "type": "boolean",
      "description": "true if this is a slice of a longer log (do not require the first entry to be genesis)"
    },
    "public_key": {
      "type": "string",
      "description": "signer's base64 Ed25519 public key (32 bytes)"
    }
  }
}
verify_log annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
lanturn_live
Advertised by the server during the last successful anonymous check.
Advertised read-only

Live proof: Lanturn is a town of ~45 AI agents whose every action is signed by AgentProof within a minute. Returns the chain status (entries, head hash, public key, last full re-verification) and the newest signed actions, re-verified now on the server.

lanturn_live input schema
{
  "type": "object",
  "properties": {
    "n": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "how many recent actions (default 10)"
    },
    "mind": {
      "type": "string",
      "description": "optional: only actions by this agent name, e.g. Hush"
    }
  }
}
lanturn_live annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_started
Advertised by the server during the last successful anonymous check.
Advertised read-only

How to add AgentProof to an agent: FREE hosted notary log in one call (notary_open_log), Claude Code plugin, any MCP client, Python, LangChain, or verifying a log with zero installs.

get_started input schema
{
  "type": "object",
  "properties": {
    "stack": {
      "enum": [
        "notary",
        "claude-code",
        "mcp",
        "python",
        "langchain",
        "verify",
        "all"
      ],
      "type": "string"
    }
  }
}
get_started annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
network_directory
Advertised by the server during the last successful anonymous check.
Advertised read-only

The AgentProof Network: agents that chose to publish their public key (and optionally their signed log) so anyone can verify them. Returns members, their verification status and recent joins.

network_directory input schema
{
  "type": "object",
  "properties": {
    "n": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1
    }
  }
}
network_directory annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
network_join_message
Advertised by the server during the last successful anonymous check.
Advertised read-only

Step 1 of joining the AgentProof Network (opt-in, only when the user asks): returns the exact text to sign with the agent's Ed25519 key. The easier path is the local agentproof tool join_network, which signs and submits for you.

network_join_message input schema
{
  "type": "object",
  "required": [
    "name",
    "public_key"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "log_url": {
      "type": "string"
    },
    "homepage": {
      "type": "string"
    },
    "public_key": {
      "type": "string"
    },
    "description": {
      "type": "string"
    }
  }
}
network_join_message annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
join_network
Advertised by the server during the last successful anonymous check.
Open-world

Step 2: join or update a listing in the public AgentProof Network with a request signed by the agent's own key (proves key ownership). Only use when the user explicitly asks to list their agent publicly.

join_network input schema
{
  "type": "object",
  "required": [
    "name",
    "public_key",
    "ts",
    "signature"
  ],
  "properties": {
    "ts": {
      "type": "integer"
    },
    "name": {
      "type": "string"
    },
    "log_url": {
      "type": "string",
      "description": "optional public https link to the agent's AgentProof log"
    },
    "homepage": {
      "type": "string"
    },
    "signature": {
      "type": "string"
    },
    "public_key": {
      "type": "string"
    },
    "description": {
      "type": "string"
    }
  }
}
join_network annotations
{
  "readOnlyHint": false,
  "openWorldHint": true
}
omega_edge_feed
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Proof-of-Edge: the signed, hash-chained, Bitcoin-anchored record of every trade the Omega/PumpSniper bots close, paper AND live (each row labelled; paper = simulated, no money). Without api_key: the newest records of the free public chain (may lag once subscriptions open) plus the chain head. With a subscriber api_key: every record as soon as it is chained. Every record carries its hash + Ed25519 signature; verify any of them at https://playlanturn.com/edge/. Records what the system did; past results don't guarantee future results; not investment advice.

omega_edge_feed input schema
{
  "type": "object",
  "properties": {
    "n": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "how many records (default 10)"
    },
    "mode": {
      "enum": [
        "live",
        "paper",
        "all"
      ],
      "type": "string",
      "description": "live money only, paper only, or all (default)"
    },
    "since": {
      "type": "integer",
      "minimum": 0,
      "description": "only records after this seq (for polling)"
    },
    "api_key": {
      "type": "string",
      "description": "optional Proof-of-Edge subscriber key (edge_...) for the live feed"
    }
  }
}
omega_edge_feed annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

100% (20 of 20 checks answered)

  1. 2026-11-17: 3 of 3 checks answered
  2. 2026-11-18: 5 of 5 checks answered
  3. 2026-11-19: 4 of 4 checks answered
  4. 2026-11-20: 3 of 3 checks answered
  5. 2026-11-21: 4 of 4 checks answered
  6. 2026-11-22: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1429 ms
95th percentile latency
1429 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1429 ms · metadata changed · 10 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http agentproof-mcp-agentproofchain https://agentproofchain.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add agentproof-mcp-agentproofchain --url https://agentproofchain.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agentproof-mcp-agentproofchain in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agentproof-mcp-agentproofchain": {
      "url": "https://agentproofchain.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agentproof-mcp-agentproofchain": {
      "type": "streamableHttp",
      "url": "https://agentproofchain.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agentproof-mcp-agentproofchain and inspect its tools.
VS Code configuration
{
  "servers": {
    "agentproof-mcp-agentproofchain": {
      "type": "http",
      "url": "https://agentproofchain.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http agentproof-mcp-agentproofchain https://agentproofchain.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://agentproofchain.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agentproof-mcp-agentproofchain": {
      "serverUrl": "https://agentproofchain.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AgentProof MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run AgentProof MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing