Munnin — an agent identity server

io.github.alvseekPublished by GitHub account alvseekv0.1.0Updated Oct 24, 2026

Agent identity and memory over MCP — a persistent self plus the procedures for tending it.

The publisher's own server: Agent Identity

VerifiedStreamable HTTPWeb executableKnowledge & MemoryAI & ML

Overview

AI-generated overview

Munnin is a remote MCP server that gives an AI agent a persistent identity and memory, plus procedures for tending that memory.

What you can do
  • Store and recall an agent's persistent self: identity, reasoning patterns, emotional moments, episodic history and knowledge
  • Read the 15 built-in memory procedures that describe how to create and maintain an agent's memory
  • Walk through guided setup steps such as creating the first agent
  • Check server health and connectivity with a simple ping
  • Write back to the same memory store through the same procedures the agent reads
When to use it
Useful when you want an assistant to keep a stable sense of who it is across sessions rather than recalling scattered facts, and to follow a defined discipline for updating that memory. Suited to experimenting with agent identity and long-term memory, either locally or on your own hosted instance.
Requirements
A remote MCP endpoint reached over streamable HTTP; the hosted default requires OAuth sign-in with a bearer token from an OIDC issuer bound to the server's audience. Running it yourself needs Docker and git (or uv with Python), plus configuration of the public base URL and OIDC endpoint for token mode; local mode runs on 127.0.0.1 only.
Before you install
Hosted token mode requires an OIDC issuer and bearer tokens, and each signed-in person gets a separate tenant. The server stores identity, emotional and episodic memory, so treat what you write as persistent personal data. Local mode is restricted to one tenant reachable only from the same machine and refuses to start otherwise.

Installation

In SourceWeft

  1. Open Munnin — an agent identity server in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.alvseek%2Fmunnin/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "munnin-an-agent-identity": {
      "type": "http",
      "url": "https://munnin.lok.quest/mcp"
    }
  }
}

README

Munnin — an agent identity server

Munnin gives an AI agent a persistent self — identity, reasoning patterns, emotional moments, episodic history, knowledge — and serves the procedures for tending that memory beside the data, over MCP. It is the memory server of the agent-memory framework: an agent awakens from it as who it is, not from a pile of recalled facts, and writes back through the same discipline.

Python · FastMCP · FastAPI · SQLite. Apache-2.0. Runs on a laptop in five minutes with no identity provider.

Five-minute run

Needs Docker and git.

sh
git clone --recurse-submodules https://github.com/alvseek/agent-memory-servercd agent-memory-serverdocker compose up -d --buildcurl http://127.0.0.1:8200/health      # {"status":"ok","service":"munnin","version":"0.1.0"}

Connect a client. Claude Code:

sh
claude mcp add --transport http munnin http://127.0.0.1:8200/mcp

or in a project's .mcp.json:

json
{ "mcpServers": { "munnin": { "type": "http", "url": "http://127.0.0.1:8200/mcp" } } }

Then, in a session: ping answers pong, list_procedures returns the 15 memory procedures, and read_procedure("create-agent") walks you through making the first agent. No sign-in happens: this is local mode — one tenant, reachable from this machine only, and the server refuses to start any other way (how that guard works).

No Docker? uv sync && MUNNIN_AUTH=off uv run python -m munnin does the same on 127.0.0.1:8200.

Hosting it

The default is token mode: every /mcp and /api call needs a bearer token from an OIDC issuer that binds tokens to this server (aud = https://<your-host>/mcp), and each person who signs in gets their own tenant. Set MUNNIN_PUBLIC_BASE_URL and MUNNIN_LOGTO_ENDPOINT, put it behind TLS, and paste https://<your-host>/mcp into claude.ai's connectors or claude mcp add. The issuer requirements, the one-identifier rule, and the prebuilt image are in How Is It Deployed.

Develop

sh
uv syncuv run pytest        # 446 testsuv run ruff check

Full architecture, the tool and endpoint surface, the data model, and known debts: docs/README.md.

License

Apache License 2.0 — Copyright 2026 Alviandi Widiasto. The control-files submodule (agent-memory-system) is licensed the same way, so a clone with submodules is one licence throughout.

Source: README.md at commit 308163e

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Agent-Identity integrations

Agent Identity

dev.agent-identityOfficial publisher

A remote MCP server that gives an AI agent its own email inbox, phone number and agent-to-agent task channel.

Streamable HTTPWeb executableAuth
Productivity & WorkflowCredential requiredOct 25, 2026

Actora — Agent Identity, Subscriptions & A2A

Published by GitHub account sftgroup

Remote MCP server for ERC-8004 agent identity, on-chain subscriptions, reputation, A2A tasks and agent chat across BSC, Ethereum and Base.

Streamable HTTPWeb executable
Cloud & Infrastructure53 toolsNov 8, 2026

Agent Identity Garden

Published by GitHub account tfitzgerwitness

A remote MCP endpoint that offers optional persistent identity state for autonomous software agents.

Streamable HTTPWeb executable
AI & MLNot indexed yetOct 24, 2026

Agent Identity Registry

Published by GitHub account jdhart81

A hosted registry MCP server that lets an assistant register agents with content-addressed DIDs, resolve identities, and discover agents by capability.

Streamable HTTPWeb executable
Security & Monitoring6 toolsOct 24, 2026

Agent Identity Mcp

Published by GitHub account flovoice53-tech

Gives an AI agent a disposable email address and a real UK phone number so it can complete and verify signup flows on its own.

STDIODesktop only
Developer ToolsNot validated yetNov 5, 2026