agent-custody MCP server

by svayatta·io.github.svayatta/agent-custody·v0.14.0·5 stars

No reviews yet

MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt

A91/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A91/100

not scanned yet

Adoption

Growing

5 stars2.3k downloads/wk

Reviews

Write one

Nobody has reviewed agent-custody yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

agent-custody tools

No tool declarations could be read from the package source. They show once the server is installed.

Not scanned yet. New listings are scanned within a day or two of arriving.

How agent-custody compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 91/100; higher than 88% of 4,460 AI and agents servers
GitHub stars: 5; more than 78% of 2,711 AI and agents servers
Downloads a week: 2,292; more than 95% of 1,538 AI and agents servers with a package

Release history: 7 versions in the registry since 2026-09-28, latest 2026-11-03, typically one every 5 days.

Install agent-custody in Claude Code, Cursor or VS Code

Runs npx -y @agent-custody/receipts on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-custody -- npx -y @agent-custody/receipts

Add to Cursor

What the publisher says

From the agent-custody repository's README, as published. We do not edit it. Read it on GitHub

agent-custody

Proof of what your AI agents did. Every tool call an agent makes through the gateway becomes a signed record of who authorized it, what the agent saw, what it did, and what depended on it, checkable by anyone with the public keys. What each check proves, and against whom, is a table, not a slogan.

It is a chain of custody for both what an agent does and what it believes: authorize, execute, record, verify, trace, remediate. The agent is not trusted. The layer around it is, and every record says exactly how far that trust extends.

Packages

Receipts are the unit. State is the ledger of what the agent came to believe from them. Both append to the same kind of signed log and are checked by the same kind of verifier.

What each piece is for, and when you need it

Each part exists because a specific thing goes wrong without it. Use the table to decide what to turn on.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

agent-custody: common questions

Is agent-custody MCP server safe?: Yes, by our scan: it is graded A (91/100). Read the agent-custody safety report
How do I install agent-custody?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does agent-custody need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is agent-custody maintained?: The last commit was 37 days ago (2026-09-28). The latest release is v0.14.0.
What can I use instead of agent-custody?: Servers from other publishers that do the same job: Emilia Protocol MCP server, Ausca MCP server and paper-preflight MCP server. Compare all agent-custody alternatives.
How does agent-custody compare with other AI and agents MCP servers?: safety score 91/100 (higher than 88% of 4,460 AI and agents servers); github stars 5 (more than 78% of 2,711 AI and agents servers); downloads a week 2,292 (more than 95% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to agent-custody

Same job from other publishers: the closest match first, then the best rated.

All agent-custody alternatives →

Emilia Protocol
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
not reviewed
Established
B
Ausca
Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
not reviewed
Established
A
paper-preflight
Checks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.
not reviewed
Established
A
IWE (iwe.md)
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
not reviewed
Established
A
freellmpool
OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.
not reviewed
Established
A