usefulweb.site Agent Permission Graph

AI infrastructure & agent explorers

Agent Permission Graph

See what your AI agent can reach: MCP servers, commands, files, network and secrets – with risks.

Secret values are masked and never returned. You can replace them with dummy values before pasting.

One per line, e.g. mcp__github__create_issue, github.*, filesystem/*.

Try an example: Claude Desktop config with typical mistakes (dummy secrets)

How it works

Paste an agent or MCP client configuration (Claude Desktop, Claude Code, Cursor, Windsurf, Cline, VS Code mcp.json, Zed) plus optional allow/deny rules and file roots. The tool draws a graph agent → servers → capabilities (commands executed, filesystem paths, network endpoints, secrets by name only) and flags risks: plaintext secrets, tokens on the command line, whole-disk or home-directory access, credential folders, unpinned packages, privileged containers, remote servers without auth or TLS, and auto-approve settings. Secret values are never shown.

  • Recognised shapes: mcpServers (Claude Desktop, Claude Code, Cursor, Windsurf, Cline), servers (VS Code mcp.json), mcp.servers (VS Code settings), context_servers (Zed). JSONC comments and trailing commas are accepted. Per server: command/args/env/cwd (stdio) or url/serverUrl/httpUrl/headers (remote), disabled, autoApprove/alwaysAllow, trust.
  • Capabilities: the executed command (and the package/image for npx, uvx, pipx, bunx, docker), filesystem paths in arguments and docker volume mounts, URLs, and secrets – environment variables and headers whose NAME looks like a credential.
  • Secrets are identified by name (KEY, TOKEN, SECRET, PASSWORD…) and by well-known token formats (sk-, ghp_, github_pat_, xox*, AKIA, glpat-, AIza, JWTs, private keys, URL credentials). Values are never output: they are replaced by ***. References like ${input:…}, ${env:…}, $VAR and placeholders do not count as plaintext.
  • Findings: tokens in args (visible in the process list), plaintext secrets in config, wide roots (/, ~, $HOME, C:\, /Users…), credential folders (~/.ssh, ~/.aws…), shells, unpinned packages/images, privileged containers or docker.sock, remote servers over HTTP or without auth headers, and auto-approve rules (incl. allow rules such as mcp__server__*).
  • The graph shows up to 60 nodes; extra capabilities per server are collapsed into a “+N more” node (full lists are in the result).

For scripts and AI agents

  • JSON API: POST https://agentpermissiongraph.usefulweb.site/api/v1/calculate (same calculation as this page)
  • Interface description: OpenAPI 3.1 · AI guide: llms.txt
  • MCP server (Streamable HTTP): https://agentpermissiongraph.usefulweb.site/mcp · tool name agent_permission_graph
Example request
curl -s -X POST https://agentpermissiongraph.usefulweb.site/api/v1/calculate \
  -H 'content-type: application/json' \
  -d '{…see OpenAPI examples…}'

Related tools

  • MCP Server Explorer – Inspect any MCP server before you connect an AI agent: tools, permissions, risks, changes over time.
  • AI Agent Tool Explorer – Index of tools AI agents can call: this site, the MCP Registry or your definitions, by capability.
  • AI Tool-Call Trace Explorer – Paste an agent transcript: see every tool call in order, with errors, timings, retries and loops.
Feedback