1. Conduid
  2. Security
  3. Limitrum
MCP server · Security

Limitrum

by · github.com/Jayden-Siete/Limitrum

Policy kernel for autonomous AI agents.

Unclaimed agent-securityai-agentsguardrailsmcpopen-sourcepolicy-enginetypescript
InstallView source
34Low

Scored 27 days ago · breakdown

About Limitrum

Limitrum is an MCP server published by Jayden-Siete in the Security category: policy kernel for autonomous AI agents.

The repository has 2 stars and 0 forks, with the last commit 5 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/Jayden-Siete/Limitrum

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Limitrum

Powered by Claude · Grounded in docs

I know everything about Limitrum. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.1.4v0.1.4 · 14 May 2026Local Verification Gateway This release adds a self-hostable HTTP verification API to the MCP server package. Added `POST /v1/verify-intent` for checking agent intents over HTTP. `GET /health` and `GET /v1/openapi.json` for local gateway…
v0.1.3v0.1.3 · 14 May 2026Agent Tool Firewall This release adds a practical path for protecting app-owned tools before execution. Added guardTool() in @limitrum/sdk for wrapping real tool handlers with Limitrum policy checks. A runnable Agent Tool Firewall example…
v0.1.2Limitrum v0.1.2 · 4 May 2026What changed Added `withLimitrumMistral` for Mistral function/tool calling. OpenAI, Anthropic, and LangChain adapters now extract real tool targets from arguments like `target`, `url`, `endpoint`, `domain`, `host`, and `apiUrl`. Added a…
v0.1.1Limitrum v0.1.1 · 2 May 2026What changed Published `@limitrum/db`, `@limitrum/sdk`, `@limitrum/cli`, and `@limitrum/mcp-server` at `0.1.1`. Added the `Integrate in 5 minutes` guide for SDK, OpenAI adapter, and MCP paths. Added a protected tool-call example that shows…
v0.1.0Limitrum v0.1.0 · 2 May 2026Limitrum v0.1.0 Official site: https://limitrum.com Limitrum is now ready as an alpha MVP for developers: a local open-source policy kernel for verifying autonomous AI agent actions before execution. Highlights TypeScript SDK with…
Questions

About Limitrum

How do I install Limitrum?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Limitrum safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Limitrum still maintained?

Yes — the latest release is v0.1.4 (14 May 2026), and the last commit was 5 months ago. The repository has 2 stars.