Back to Browse

Sovereign Agent Logbook MCP Server

Developer ToolsLow Risk8.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Tamper-evident logbook for AI agents: hash-chained, on your own server, any model via MCP.

About

Tamper-evident logbook for AI agents: hash-chained, on your own server, any model via MCP.

Security Report

8.0
Low Risk8.0Low Risk

Valid MCP server (2 strong, 3 medium validity signals). 4 known CVEs in dependencies Package registry verified. Imported from the Official MCP Registry.

12 files analyzed · 5 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

file_system

Check that this permission is expected for this type of plugin.

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "sovereign-agent-logbook": {
      "command": "uvx",
      "args": [
        "sovereign-agent-logbook==0.1.3"
      ]
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

Sovereign Agent Logbook

Every AI agent needs a logbook. Yours should stay in Europe.

An open-source, tamper-evident logbook for AI agents. It records each action, tool call and human approval your agent logs in an append-only, hash-chained file on your own server. Each entry says who, what, why, approved by whom and with what outcome. It works with any model (Mistral, GPT-NL, Llama, Claude, GPT…) because it speaks the open Model Context Protocol.

CI Licence: Apache-2.0 Status: v0.1 — early, working, tests passing

v0.1 is a working skeleton, not a finished product. It logs, chains, masks secrets, verifies and exports, and every claim on this page has a test behind it. What it does not do yet is listed honestly in ROADMAP.md.

Follow the build. Get the release notes by email at delfen.ai/logbook (a few mails a year, plus the weekly Delfen CTO update; unsubscribe any time). Found a hole in the threat model, or an event field that does not fit your agents? Open an issue. If the logbook is useful to you, a star helps other people find it.

Why

The EU AI Act requires providers and deployers of high-risk AI systems to keep logs and keep a human able to intervene (Articles 12, 14 and 26(6)). Those duties were due on 2 August 2026, or 2 August 2027 for AI built into regulated products. That changed with the Digital Omnibus on AI (Regulation (EU) 2026/1744, in force 27 July 2026). It moved them to 2 December 2027 for most high-risk systems and 2 August 2028 for AI built into regulated products. The clock moved; it did not stop. Reporting serious incidents (Article 73) sits in a different chapter of the Act, outside that postponement; check its timing for your system. The logbook gives you a verified timeline of the agent's logged actions to report from.

Autonomous agents make those duties harder. One task is ten tool calls, and when something goes wrong nobody can reconstruct which call did what, on whose approval.

Most tools for this live inside a US cloud platform or are built for one model vendor. If you run a sovereign setup — an open-weight model on your own hardware — there is nothing small and neutral to drop in. This is that thing.

What you get

  • A tamper-evident log. Each event carries the hash of the previous one. Change, insert, remove or reorder a line and logbook verify tells you exactly where. (How, in one file of about 80 lines)
  • Any model, any host, or no cloud at all. Four MCP tools: log_event, verify_logbook, recent_events, export_logbook.
  • Secrets masked before writing. Keys that look like passwords, tokens, API keys, IBANs or BSNs are replaced with ***masked*** before hashing.
  • No outbound network, proven by a public test. The test blocks outbound socket connections in the Python runtime and still completes a full write, verify and export cycle. A second test asserts that the logbook core imports no HTTP client. (tests/test_no_network.py)
  • Audit-ready export. JSON and CSV your DPO or auditor can read without this tool.
  • An open format. SPEC.md is the log format, separate from the code, Apache-licensed, so other tools can write it too.
  • A Skills pack that teaches any agent when to log, what to write and when to stop and ask a human. (skills/sovereign-agent-logbook/SKILL.md)

Five-minute install

Needs Python 3.11 or newer. On an older Python, pip reports that it cannot find the package; check with python3 --version. The Python that ships with macOS is 3.9.

pip install sovereign-agent-logbook

Point your MCP-capable agent host at the server over stdio. For Claude Desktop / Claude Code, Cursor, Continue, or any host with an mcpServers block:

{
  "mcpServers": {
    "logbook": {
      "command": "sovereign-agent-logbook",
      "env": { "LOGBOOK_PATH": "/var/lib/logbook/agent.jsonl" }
    }
  }
}

Installed once for the whole machine? Then every agent host on it starts the same server, and a fixed path sends every project's actions to one file. Put {project} in the path to give each project its own file:

"env": { "LOGBOOK_PATH": "~/logbooks/{project}.jsonl" }

{project} is the name of the folder the agent works in (the nearest folder with a .git in it). {cwd} is that working folder itself. Most hosts start the server in the project folder; the logbook://about resource shows which file is in use. We added this after a session on one project wrote into another project's log on our own machine.

Or run it as a service on your own box with Docker:

docker build -t sovereign-agent-logbook .
docker run -d --name logbook \
  -p 127.0.0.1:8765:8765 \
  -v logbook-data:/data \
  sovereign-agent-logbook
# MCP endpoint: http://127.0.0.1:8765/mcp   (put TLS in front for anything beyond localhost)

Then, at any time, as a human:

logbook --path /var/lib/logbook/agent.jsonl verify
logbook --path /var/lib/logbook/agent.jsonl export --format csv > audit.csv
logbook --path /var/lib/logbook/agent.jsonl tail --limit 10

From a script, cron job or CI pipeline that does not speak MCP, write an event with logbook log:

logbook --path /var/lib/logbook/backup.jsonl log \
  --agent nightly-backup --model none --action dump_database \
  --approval auto --approval-rule "runbook 4" \
  --outcome success --summary "dump written" --arg target=db1

If an entry turns out to be wrong, do not edit the file: that breaks the chain, and verify will say so. Append a correction that points to the wrong entry by its seq:

logbook --path /var/lib/logbook/backup.jsonl log \
  --agent nightly-backup --model none --action dump_database \
  --outcome error --corrects 41 \
  --summary "entry 41 said success; the dump had not run"

The wrong entry stays visible and the correction says what was wrong. We learned this from our own agents: one logged a push as done before it had run.

Several processes on one machine may append to the same file: writes take a file lock (POSIX). Writers on different machines, for example agents that sync the file through git, should each keep their own file, because two copies appended separately fork the chain.

What an event looks like

{"spec":"0.1","seq":42,"id":"…","ts":"2026-11-05T20:41:03.123456+00:00",
 "prev_hash":"9f2c…","hash":"3a1b…",
 "agent_id":"invoice-bot","model":"mistral-small-4",
 "action":"pay_invoice","arguments":{"amount":1250,"iban":"***masked***"},
 "reason":"Invoice 2026-118 matches PO 4471 and is under the auto-approval limit",
 "approval":"auto","approved_by":null,"approval_rule":"pay-under-2000-matched-po",
 "outcome":"success","result_summary":"Paid via bank API, ref 88213",
 "run_id":"task-7f3e","tags":["finance"]}

Field meanings are normative in SPEC.md. Every call to log_event needs agent_id, model and action; the logbook rejects a call without them. model is required on purpose: an auditor needs to see which model version took each action.

Trust: no black box

What we promiseHow you can check it yourself
Tamper-evidentEdit any line of a logbook file, run logbook verify
No outbound networktests/test_no_network.py; the Dockerfile adds no network tooling
Tests are public and run on every changeThe CI badge above links to every run
We say what it does not protect againstTHREAT-MODEL.md
We say which AI Act articles it helps with, and which it does notdocs/ai-act-mapping.md
The format outlives the softwareSPEC.md, Apache-2.0
Security issues have a processSECURITY.md
Decisions are recordedROADMAP.md, CHANGELOG.md

Not tied to one platform

GitHub is where most developers look, so this is the working repository. An identical mirror on EU-hosted infrastructure is planned so that the code never depends on a single platform; the target is being chosen and will be recorded in ROADMAP.md. Until then, git clone gives you a complete copy — that is the point of git.

Hosted version

If you would rather not run a server, a hosted version on EU-only infrastructure (Hetzner, Germany / Scaleway, France) with retention policies, daily signed anchoring of the chain and a monthly audit export is planned. Terms as offered on delfen.ai/logbook: €29 per month excluding VAT, 30-day free trial, cancel any time; if the hosted version is not live by the end of a trial, the trial is cancelled rather than charged.

Licence

Apache License 2.0. Built in the Netherlands by Delfen. Contributions welcome — see CONTRIBUTING.md.

Reviews

No reviews yet

Be the first to review this server!