We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

Trustabl Agent Reliability Analyzer

MCP server by Trustabl

Scan agent code for reliability and safety gaps across nine agent SDKs, then apply fixes to the source.

Runs locally (Runs on your machine: its page has the install command)Runs with docker

Install Trustabl Agent Reliability Analyzer

Runs on your machine. Your client starts it with this command:

docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.15

Needs Docker on your computer. The setup steps below show where the command goes in each client.

Share this server

Opens this page, with the install command and setup steps.

mcp.tc/i/trustabl-agent-reliability-analyzer

About

Agent Reliability Analyzer is a deterministic static scanner for AI agent code. It finds issues such as vague tool descriptions, missing timeouts and retries, untyped parameters, absent guardrails, excessive tool grants and unbounded agent loops. It covers nine SDKs, including Claude Agent SDK, OpenAI Agents SDK, Google ADK, MCP servers, LangChain/LangGraph, CrewAI, AutoGen/AG2, Pydantic AI and the Vercel AI SDK. Output can be human-readable, JSON or SARIF.

It runs locally over stdio, as a Docker image or through the trustabl CLI with the mcp command. Scanning runs on your machine with no account, no network and no code upload. Applying fixes with the enrich step needs your own Anthropic, OpenAI or Google API key.

What you can do

  • Scan an agent repository for reliability and safety findings
  • Score each tool, agent, subagent and skill surface separately
  • Detect missing timeouts, retries, guardrails and untyped parameters
  • Flag tool grants that exceed an agent's stated purpose
  • Export results as JSON or SARIF 2.1.0
  • Preview and apply suggested fixes to source files

Tools

Local servers list their tools once they’re running, and this one doesn’t publish its list in advance. Your client shows them after you add it.

Example prompts

  • Scan this repository for agent reliability issues.

  • Which tools in my agent have no timeout or vague descriptions?

  • Show the diff of fixes for the findings in scan.json.

  • Does any subagent in this repo have Bash access it shouldn't?

Set up

Every client starts Trustabl Agent Reliability Analyzer on your machine with the same command. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio trustabl-agent-reliability-analyzer -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.15
  1. Start Claude Code and type /mcp. trustabl-agent-reliability-analyzer should show as connected.

Add --scope user to make it available in every project.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "trustabl-agent-reliability-analyzer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.15"
      ]
    }
  }
}
  1. Save the file and restart Claude Desktop.

Needs Docker on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "trustabl-agent-reliability-analyzer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.15"
      ]
    }
  }
}

Needs Docker on your computer.

VS Code

Or from a terminal:

code --add-mcp '{"name":"trustabl-agent-reliability-analyzer","type":"stdio","command":"docker","args":["run","-i","--rm","ghcr.io/trustabl/agent-reliability-analyzer:0.1.15"]}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "trustabl-agent-reliability-analyzer": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.15"
      ]
    }
  }
}

Needs Docker on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "trustabl-agent-reliability-analyzer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.15"
      ]
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add trustabl-agent-reliability-analyzer -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.15

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.trustabl-agent-reliability-analyzer]
command = "docker"
args = ["run", "-i", "--rm", "ghcr.io/trustabl/agent-reliability-analyzer:0.1.15"]

Needs Docker on your computer.

Gemini CLI

gemini mcp add trustabl-agent-reliability-analyzer docker -- run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.15

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "trustabl-agent-reliability-analyzer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.15"
      ]
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs Docker on your computer.

Embed

Show Trustabl Agent Reliability Analyzer in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![Trustabl Agent Reliability Analyzer on mcp.tc](https://mcp.tc/i/trustabl-agent-reliability-analyzer/badge.svg)](https://mcp.tc/i/trustabl-agent-reliability-analyzer)
HTML
<a href="https://mcp.tc/i/trustabl-agent-reliability-analyzer"><img src="https://mcp.tc/i/trustabl-agent-reliability-analyzer/badge.svg" alt="Trustabl Agent Reliability Analyzer on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/trustabl-agent-reliability-analyzer.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/trustabl-agent-reliability-analyzer" title="Trustabl Agent Reliability Analyzer on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/trustabl-agent-reliability-analyzer.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Trustabl Agent Reliability Analyzer card to your site.

Markdown
Add the mcp.tc card for Trustabl Agent Reliability Analyzer, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/trustabl-agent-reliability-analyzer.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="trustabl-agent-reliability-analyzer"><a href="https://mcp.tc/i/trustabl-agent-reliability-analyzer">Trustabl Agent Reliability Analyzer on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![Trustabl Agent Reliability Analyzer on mcp.tc](https://mcp.tc/i/trustabl-agent-reliability-analyzer/badge.svg)](https://mcp.tc/i/trustabl-agent-reliability-analyzer)
```

Reference: https://mcp.tc/embed

Change history

It runs on your computer and has no package we can follow. Edits by its owner show up here.

Follow Trustabl Agent Reliability Analyzer and we’ll email you when something changes.

Nothing recorded yet. Edits by the server’s owner will show up here.

FAQ

Can I paste mcp.tc/i/trustabl-agent-reliability-analyzer into my MCP client?

No. Trustabl Agent Reliability Analyzer runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.15.

Does Trustabl Agent Reliability Analyzer need an API key?

No. It doesn’t declare any keys or environment variables. It runs with your user account’s permissions, so check what its tools can reach.

Is Trustabl Agent Reliability Analyzer a remote or a local server?

Local. Your client starts it as a process on your computer with docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.15, which needs Docker.

What can Trustabl Agent Reliability Analyzer do?

You can scan an agent repository for reliability and safety findings, score each tool, agent, subagent and skill surface separately and detect missing timeouts, retries, guardrails and untyped parameters.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Does mcp.tc track changes to Trustabl Agent Reliability Analyzer?

Partly. Trustabl Agent Reliability Analyzer runs on your computer and has no package we can follow, so its History tab shows only edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read Trustabl Agent Reliability Analyzer’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with Trustabl. This page was built from Trustabl Agent Reliability Analyzer’s public metadata, last checked on 1 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.