MCP.so
Sign In

Agent Trust (mnki-mcp) MCP ServerVerifiedFeatured

@MNKIAgentOS

Basic information

Category

Developer Tools

Last updated

License

Apache-2.0

Author

MNKIAgentOS

Submitted by

javmann100

About Agent Trust (mnki-mcp) MCP Server

Agent Trust — open profile + reference implementation for proving what an autonomous AI agent is authorized to do: identity, delegation with attenuation, proof-of-possession, attestations, tamper-evident provenance. Buil

Agent Trust (mnki-mcp) MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "agent-trust": {
      "command": "npx",
      "args": [
        "mnki-cli",
        "demo",
        "#",
        "the",
        "15-second",
        "story,",
        "no",
        "account:",
        "a",
        "€47,000",
        "refund",
        "denied,",
        "€420",
        "allowed"
      ]
    }
  }
}

Agent Trust (mnki-mcp) MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Agent Trust (mnki-mcp)?

Agent Trust (mnki-mcp) is a local MCP proxy that sits between your MCP client and any MCP server and checks every tools/call against an agent's identity, delegated authority and policy before it reaches the server, returning signed evidence for each decision.

It is part of Agent Trust by MNKI, an open profile and reference implementation for proving what an autonomous AI agent is authorized to do: identity, delegation with attenuation, proof-of-possession, attestations and tamper-evident provenance, built on JWS, OAuth/OIDC, SPIFFE/WIMSE, AuthZEN, OpenID Federation, MCP and A2A. The proxy, CLI, SDKs and verifier are open source under Apache-2.0 and work in local mode with no account. A hosted console at mnki.com adds approvals, a ledger and a fleet view.

How to use Agent Trust (mnki-mcp)?

You need Node.js. Start with the demo, which needs no account:

npx mnki-cli demo

An invoice agent may refund up to €5,000: €47,000 is denied with the evidence list, €420 is allowed and €3,200 needs a human.

To protect the MCP servers you already run, scan the machine, then let mnki protect rewrite your client config. It is a dry run by default and starts in observe mode:

npx mnki-cli scan
npx mnki-cli protect --client cursor --server github --agent my-agent
npx mnki-cli protect --client cursor --server github --agent my-agent --apply
npx mnki-cli protect report --server github

mnki protect rollback undoes the change. Add --mode enforce when you are ready to block calls.

Claude Desktop

By hand, a stdio server entry wraps the original command after --upstream --:

{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "mnki-mcp", "--agent", "agt_your_agent", "--server", "github", "--mode", "observe", "--upstream", "--", "npx", "-y", "@modelcontextprotocol/server-github"],
      "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_TOKEN", "MNKI_URL": "https://mnki.com", "MNKI_API_KEY": "YOUR_MNKI_API_KEY" }
    }
  }
}

MNKI_URL and MNKI_API_KEY (or mnki init) tell the proxy which console verifies; MNKI_IDENTITY_FILE points at the agent key for signed requests.

Claude Code

Add the same entry as JSON:

claude mcp add-json github '{"command":"npx","args":["-y","mnki-mcp","--agent","my-agent","--server","github","--mode","observe","--upstream","--","npx","-y","@modelcontextprotocol/server-github"]}'

Cursor

For a remote HTTP server, point the proxy at the upstream URL:

{
  "mcpServers": {
    "billing": {
      "command": "npx",
      "args": ["-y", "mnki-mcp", "--agent", "agt_your_agent", "--server", "billing", "--mode", "enforce", "--amount-map", "create_payment=amount:currency", "--upstream-url", "https://mcp.example.com/mcp", "--upstream-header", "Authorization=Bearer YOUR_UPSTREAM_TOKEN"]
    }
  }
}

VS Code

{
  "servers": {
    "playwright": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mnki-mcp", "--agent", "agt_your_agent", "--server", "playwright", "--mode", "warn", "--upstream", "--", "npx", "@playwright/mcp@latest"]
    }
  }
}

The repository also has a Windsurf snippet and a Docker sidecar image, ghcr.io/mnkiagentos/mnki-mcp.

Key features of Agent Trust (mnki-mcp)

  • Verifies every tools/call and forwards everything else untouched.
  • Wraps stdio commands or Streamable HTTP endpoints.
  • Four modes: observe (log only, the default), warn, require_approval and enforce.
  • Clear JSON-RPC errors in enforce mode: -32003 denied with evidence, -32001 approval required, rejected or expired, -32005 verification quota exceeded and -32006 Agent Trust unreachable.
  • Works offline in local mode; connect the console for human approvals, central policy and a tamper-evident ledger.
  • Same verification core in TypeScript, Python (pip install mnki) and Go, checked by open conformance vectors for levels 1 to 3.
  • Releases carry npm and PyPI provenance, SBOMs and cosign-signed checksums.

Use cases of Agent Trust (mnki-mcp)

  • Shadow-test a policy: run the GitHub MCP server through the proxy in observe mode, then read mnki protect report to see what would have been denied.
  • Cap payments: on a billing MCP server, map create_payment amounts with --amount-map and enforce a refund limit, so €47,000 is denied and €420 runs.
  • Human approval: in require_approval or enforce mode, risky calls wait for a person to approve from the console.
  • Audit: keep a signed record of which agent called which tool under which delegation.
  • Inventory: npx mnki-cli scan lists every MCP server and API key agents can use on a machine.

Troubleshooting Agent Trust (mnki-mcp)

  • Nothing is blocked. The default mode is observe, which only logs. Switch to --mode enforce once the report looks right.
  • -32006 errors. Agent Trust is unreachable. In observe and warn modes the proxy forwards instead; check MNKI_URL and your network.
  • -32005 errors. You hit the verification quota. The free cloud plan includes 10,000 hosted verifications a month.
  • The wrong config was changed. mnki protect shows a diff first; use mnki protect rollback to undo an applied change.

Frequently asked questions

1

Is mnki-mcp an MCP server with its own tools?

No. It is a proxy. It adds no tools of its own; it verifies tool calls to the server it wraps and forwards everything else.

2

Is it free?

The proxy, CLI, SDKs and verifier are Apache-2.0 open source and work locally with no account. The hosted console has a free tier with 10,000 verifications a month, plus paid plans.

3

Do I need an account?

No for local mode and the demo. Connecting the console at mnki.com needs an API key from Settings, API keys.

4

Which clients does it support?

The docs list Claude Desktop, Claude Code, Cursor, Windsurf and VS Code, with ready-made snippets for Claude Desktop, Cursor, Windsurf and VS Code.

5

Does it work with remote MCP servers?

Yes. Use `--upstream-url` and `--upstream-header` to wrap a Streamable HTTP endpoint.

6

Can I undo the config change?

Yes. `mnki protect rollback` restores the client config.

Comments

More Developer Tools MCP servers