Skip to main content
ClaudeWave

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. Built on JWS, OAuth/OIDC, SPIFFE/WIMSE, AuthZEN, OpenID Federation, MCP and A2A.

MCP ServersOfficial Registry0 stars0 forksTypeScriptApache-2.0Updated today
ClaudeWave Trust Score
95/100
Verified
Passed
  • Open-source license (Apache-2.0)
  • Actively maintained (<30d)
  • Clear description
  • Topics declared
  • Documented (README)
Last scanned: 9/18/2026
Install in Claude Code / Claude Desktop
Method: NPX · mnki-cli
Claude Code CLI
claude mcp add agent-trust -- npx -y mnki-cli
claude_desktop_config.json (Claude Desktop)
{
  "mcpServers": {
    "agent-trust": {
      "command": "npx",
      "args": ["-y", "mnki-cli"]
    }
  }
}
1. Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
2. Replace any <placeholder> values with your API keys or paths.
3. Restart Claude. The MCP server and its tools appear automatically.
Use cases

MCP Servers overview

# Agent Trust

**Prove what an autonomous AI agent is authorized to do.** An open profile plus a reference
implementation for agent identity, principal binding, delegation with attenuation,
capability-based authorization, request proof-of-possession, authorization attestations,
tamper-evident provenance and revocation — carried on JWS, OAuth/OIDC, SPIFFE/WIMSE, AuthZEN,
OpenID Federation, MCP and A2A. No new cryptography, no new protocol.

> No consequential agent action should be accepted because a process is running or a token is
> valid. It should be accepted because the action is attributable, authorized, constrained,
> current and verifiable.

| Package | What it is |
|---|---|
| [`packages/verifier`](packages/verifier) | The pure core: parsing, delegation chain + attenuation, policy engine, request proof, delegation credentials, attestations, the 12-step evidence pipeline. Deterministic, dependency-free, WebCrypto only. |
| [`packages/sdk-ts`](packages/sdk-ts) | `mnki-sdk` — TypeScript SDK: agent identity (keys, signed requests), `guard()` for any tool call, verify, delegate, attest, offline verification against an organization's JWKS; framework adapters as subpaths. |
| [`packages/cli`](packages/cli) | `mnki-cli` — `mnki demo · init · identity · verify · inspect · delegate · attest · scan · protect · conformance` (`agenttrust` is an alias). |
| [`packages/mcp`](packages/mcp) | `mnki-mcp` — a local MCP proxy that verifies every `tools/call` before it reaches the server (`mnki protect` installs it). |
| [`python/`](python) | `pip install mnki` — Python SDK (zero dependencies; `mnki[signing]` for Agent-Proof). |
| [`go/`](go) | Go verifier (same vectors, no dependencies) and **`at-verify`**, the self-hosted verifier that serves `/v1/verify` from an exported organization snapshot. |
| [`spec/`](spec) | **Agent Trust Profile v0.1**, the interoperability positioning, the Internet-Draft (`draft-mnki-agent-trust-profile-00`) and the standards plan. |
| [`conformance/`](conformance) | Executable vectors for **certification levels 1–3** (`LEVELS.md`) — the cross-language contract; TypeScript and Go runners pass them all. |

```bash
npx mnki-cli demo      # the 15-second story, no account: a €47,000 refund denied, €420 allowed
npx mnki-cli scan      # find the MCP servers and API keys agents can use on this machine
npm install mnki-sdk   # guard() any tool call
pip install mnki               # same in Python
```

Develop against the open verifier and SDKs for free; govern fleets with the hosted control plane at
[mnki.com](https://mnki.com) — see [COMMERCIAL.md](COMMERCIAL.md) for the boundary and
[TRADEMARK.md](TRADEMARK.md) for name and badge use. Releases carry npm/PyPI provenance, SBOMs and
cosign-signed checksums ([SECURITY.md](SECURITY.md)).

Apache-2.0.
a2aagent-securityai-agentsauthorizationauthzendelegationdpopgolangjwsmcpopenid-federationprovenancepythonspiffetypescriptwimsezero-trust

What people ask about agent-trust

What is MNKIAgentOS/agent-trust?

+

MNKIAgentOS/agent-trust is mcp servers for the Claude AI ecosystem. 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. Built on JWS, OAuth/OIDC, SPIFFE/WIMSE, AuthZEN, OpenID Federation, MCP and A2A. It has 0 GitHub stars and its last recorded update is dated 2026-09-17.

How do I install agent-trust?

+

You can install agent-trust by cloning the repository (https://github.com/MNKIAgentOS/agent-trust) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is MNKIAgentOS/agent-trust safe to use?

+

Our security agent has analyzed MNKIAgentOS/agent-trust and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains MNKIAgentOS/agent-trust?

+

MNKIAgentOS/agent-trust is maintained by MNKIAgentOS. The last recorded GitHub activity is dated 2026-09-17, with 0 open issues.

Are there alternatives to agent-trust?

+

Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.

Deploy agent-trust to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: MNKIAgentOS/agent-trust
[![Featured on ClaudeWave](https://claudewave.com/api/badge/mnkiagentos-agent-trust)](https://claudewave.com/repo/mnkiagentos-agent-trust)
<a href="https://claudewave.com/repo/mnkiagentos-agent-trust"><img src="https://claudewave.com/api/badge/mnkiagentos-agent-trust" alt="Featured on ClaudeWave: MNKIAgentOS/agent-trust" width="320" height="64" /></a>

More MCP Servers

agent-trust alternatives