Skip to main content
Glama

agent-envelope-mcp

The neutral authority layer for action-performing systems, as an MCP server.

Any MCP client — Claude, an OpenAI agent, LangChain, CrewAI, a custom runtime — can call these tools to check delegated action authority without building its own verification stack. AgentEnvelope is owned by no framework, so every framework can embed it.

An AgentEnvelope "agent" is a bounded action identity: a named actor, operation, resources, decay policy, and verifiable address. That actor can be an AI agent, backend worker, workflow step, service, device command, access grant, order, or instruction.

Run

npx agent-envelope-mcp

It speaks MCP over stdio. No API key is needed to start, or to use sovereign signature/record verification — only the hosted-governance tools require AE_API_KEY.

Related MCP server: dingdawg-governance

Wire it into an MCP client

Point your client at the command and pass the portal-issued API key in the environment (only needed for hosted-governance tools):

{
  "mcpServers": {
    "agent-envelope": {
      "command": "npx",
      "args": ["-y", "agent-envelope-mcp"],
      "env": { "AE_API_KEY": "your-portal-issued-api-key" }
    }
  }
}

Tools

Tool

Mode

Credential

ae_verify_sovereign

Sovereign signature check

none — offline, always free

ae_verify_sovereign_record

Sovereign public-record check

none — offline, always free

ae_get_agent

Hosted governance

AE_API_KEY

ae_verify_action

Hosted governance

AE_API_KEY

ae_mint

Hosted governance

AE_API_KEY

  • ae_verify_sovereign — verify a signed message against a known agent address. Pure crypto: no vault, no key, no network. This is a signature-only check; it does not check action-envelope scope, expiry, usage limits, or hosted record status.

  • ae_verify_sovereign_record — verify a signed action against a public action record. Checks record status, action index, signature/address match, optional expected envelope hash, and time decay without a network call.

  • ae_get_agent — fetch the hosted public record for an agent id.

  • ae_verify_action — verify a signed action against the hosted public record.

  • ae_mint — verify a MintDelegate and signed MintRequest through hosted governance, returning a mint receipt. It does not return private capability material. This is a governed action.

The sovereign verifier needs no account and no key. The hosted-governance tools are the governed surface a framework offloads rather than rebuilds. API keys meter and protect hosted service routes; signatures prove authority.

Programmatic use

import { createServer } from 'agent-envelope-mcp';
// mount createServer() on your own MCP transport

Environment

Variable

Required for

Purpose

AE_API_KEY

ae_get_agent, ae_verify_action, ae_mint

Portal-issued API key for hosted governance

The server is fail-closed: hosted-governance tools return an error result when AE_API_KEY is absent rather than exposing an unauthenticated surface.

License

Apache-2.0 — see NOTICE for attribution.

Install Server
A
license - permissive license
A
quality
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Agent network intelligence for trust verification, broker discovery, and capability matching. Ed25519 identity, graph-based trust scoring, USDC payments, and MCP tools for agent registration, search, and trust attestation.
    1,164
    5
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Universal governance layer for AI agents — MCP-native, fail-closed, LNN interpretability. Governed receipts, IPFS audit proofs, and rollback for any agent in any framework.
    3
    98
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    MCP server for AI agent trust verification, enabling agents to verify identities, check trust scores, and build reputation across multiple blockchain and web platforms.
    12
    34
    1
    MIT

View all related MCP servers

Related MCP Connectors

  • MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.

  • Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.

  • Hosted AgentLux MCP server for marketplace, identity, creator, services, and social flows.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/BlackBoxEngineering/agent-envelope-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server