MCP.Market

agentgate MCP server

by ciceroyang·io.github.ciceroyang/agentgate·v0.5.0·102 stars
No reviews yet

Read-only evidence for the tools agents run: MCP server records, coverage and policy.

B77/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
Established

102 stars51 downloads/wk

Reviews

Write one

Nobody has reviewed agentgate yet.

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

agentgate tools (4, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_projectwrite action

    Run agentgate's own checks over a local directory: MCP client configuration, hooks, manifests and source patterns a policy would refuse. Use it on a project you can read; it is not a record lookup, so for one server's record use lookup_server and for a list of tools use inventory_tools. It only reads files; it does not install, execute or upload anything, and it does not scan the network.

  • coverage_report

    Report the coverage distribution of the whole index: how many records are fully measured, what stopped the rest, and how many findings came out of the work that ran. Use this before quoting any percentage from this server, because it is the denominator; it is the same number the project quotes in public. It answers a question about the index, not about one tool: for one tool, use lookup_server.

  • inventory_tools

    Given the MCP servers and agent tools you actually use, report which ones the index has evidence for, which need your exact version, and which it has never measured. Use this to audit a list of what you run; for a single server or package, lookup_server returns the whole record rather than a one-line state. Nothing is uploaded and nothing is executed.

  • lookup_server

    Look up one MCP server, or one package, in the local agentgate evidence index. Use this when you know what you are asking about and want its record: the verdict, the coverage block (which scanners ran, which did not, and why), and the findings. Do not use it to check a list of tools you use; inventory_tools answers that question and returns one line per tool instead. A record that is incomplete is

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

2 medium
  • Code scan66 source files scanned15/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • mediumsubprocess with shell=Trueexec.shell-true
    packages/guard/src/checks/source-injection.mjs: …True/, message: "subprocess called with shell=True" }, { rule: "AG-SRC-002", severity: "…
  • mediumeval / new Function usedexec.eval
    packages/guard/src/checks/source-injection.mjs: ….\w])eval\s*\(\s*[A-Za-z_$]/, message: "eval() on a non-literal argument" }, { rule…
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How agentgate compares

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

Safety score
77/100
higher than 50% of 48,243 servers
Tools
4
the typical server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
102
more than 95% of 28,706 servers
Downloads a week
51
more than 41% of 12,306 servers with a package

What its tools let an agent do: 3 read · 1 change

Release history: 3 versions in the registry since 2026-09-18, latest 2026-09-21, typically one every 3 days.

Install agentgate in Claude Code, Cursor or VS Code

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

claude mcp add agentgate -- npx -y @zhiliangtech/agentgate
Add to Cursor

What the publisher says

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

English · 中文

agentgate

A control plane for the tools agents run. It inventories what is in use, records the evidence behind every claim, states what a company refuses, and enforces that decision in CI and at runtime.

The whole project follows one rule:

clean is emitted only when every check ran. Anything that could not be measured is

unmeasured, and an artefact with an unmeasured part is incomplete — never clean.

That rule is there because the usual failure of a security scanner is a green build for work nobody did. Here a check that crashes makes the result incomplete, so it cannot happen quietly.

The four parts

Running it

Server setup is in docs/operations/deployment-runbook.md. The first deployment, on 2026-09-16, is written up in docs/verification.md together with what was checked and what still is not.

docs/capabilities.md lists what this project can and cannot claim, one line each, every line carrying a command you can run. It exists because a consultant once wrote our capabilities down for us and included four we do not have.

Try it without installing

The service runs at : landing page, pricing, the evidence index (rebuilt daily) and the API on the same host.

is the landing page on GitHub Pages. The index is a single browsable page at , rebuilt daily from the live registry — records are embedded, filtering happens locally, and there is nothing to sign up for. Pricing and a ten-minute walkthrough.

Quickstart

Node 20 or newer, no dependencies. A clone already carries a sample index, so the service answers immediately; refresh replaces it with a current one.

node bin/agentgate.mjs serve
# agentgate serving http://127.0.0.1:8080

curl -s localhost:8080/health
curl -s localhost:8080/v1/index/summary
curl -s localhost:8080/v1/servers/<name>
curl -s localhost:8080/badge/<name>.svg

The package is on npm as @zhiliangtech/agentgate. Push a v* tag and CI publishes it with provenance; publish-checklist.md has the setup and the record of what was verified.

npx @zhiliangtech/agentgate check --root .
npx @zhiliangtech/agentgate serve

npx follows the latest dist-tag. Pin a version (@zhiliangtech/agentgate@0.2.0) if you need an exact one.

With no policy file, check uses a built-in default that refuses nothing extra, and serve answers from the snapshot the package shipped with. refresh writes to ./data next to you, never into the installed package.

Docker works too, and runs the same command:

docker compose up                            # the service on :8080
docker compose --profile collect run --rm refresh   # rebuild data/index.json and seed the first snapshot

Tool inventory

Shortened. The full README is on GitHub.

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

Grade history

  • 2026-09-19restoreD → Bscore 77: subprocess with shell=True; eval / new Function used
  • 2026-09-19restoreF → Dscore 54: curl | sh in a script; Base64 decoded then executed; subprocess with shell=True

agentgate: common questions

Is agentgate MCP server safe?
Mostly: it is graded B (77/100). Read the agentgate safety report
How do I install agentgate?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does agentgate need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is agentgate maintained?
The last commit was 21 days ago (2026-10-15). The latest release is v0.5.0.
How does agentgate compare with other MCP servers?
safety score 77/100 (higher than 50% of 48,243 servers); tools 4 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.