agentguard
io.github.MukundaKatta/agentguard
Network-egress firewall for agent tools: check URLs against a declarative policy.
Description as published in the official MCP registry.
What we measured
| Endpoint | None listed (runs locally) | registry |
|---|---|---|
| GitHub stars | 1 | github.com/MukundaKatta/agentguard-mcp |
| Last push | 2026-08-01 | GitHub API |
| Licence | MIT | GitHub API |
| Registry version | 0.1.0 · active · updated 2026-04-27 | registry |
| Package | npm: @mukundakatta/agentguard-mcp | registry |
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows a real call went through, not just an opinion. How to file one.
Connect
npx -y @mukundakatta/agentguard-mcpCommands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.
Related servers
- agentguard — policy proxy for agent tool calls Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy…
- agentcast Structured-output enforcer: extract and validate JSON from messy LLM text.
- agentfit Token-aware message truncation: fit a chat history into your model's context budget.
- agentvet Validate tool-call args before execution. Returns LLM-friendly retry hints.
- agentguard47 Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
- agentsnap Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
Badge for your README
Shows the result of our latest check and links back to this page.
[](https://openforallofus.com/tools/io.github.MukundaKatta/agentguard)Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.github.MukundaKatta/agentguard.