Skip to content
Back to the index

mcp-guardbench

PyPIInfrastructure

PulseGate's liveness check found it on 2 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 2 Oct 2026. How this is checked

mcp-guardbench is an open-source benchmark and runtime evaluation framework for testing the security of Model Context Protocol tool-using agents. It helps developers and security researchers assess threats such as tool poisoning and rug-pull behavior.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI
1star
6features
2026since

Overview

6 features

Purpose: Evaluating and detecting security risks in Model Context Protocol tool-using agents.

Inferred · not functionally tested

Audience: AI security researchers and developers building MCP agents

Inferred · not functionally tested

Functions: agents

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

mcp-guardbench sits in PulseGate's Agent evaluation & testing category. Inferred · not functionally tested: It focuses on evaluating and detecting security risks in Model Context Protocol tool-using agents. Inferred · not functionally tested: mcp-guardbench is an open-source project aimed at AI security researchers and developers building MCP agents. Basis unknown · not verified: mcp-guardbench is open source under the MIT license. Basis unknown · not verified: It runs on the command line, and it can be self-hosted.

It is developed by Manish Maurya, and it first shipped in 2026. The project is developed in the open on GitHub with 9 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are security benchmarking, runtime evaluation, and MCP scanning. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Security benchmarking
  • Runtime evaluation
  • MCP scanning
  • Tool poisoning detection
  • Rug-pull detection
  • Agent testing

Topics: Inferred · not functionally tested

Tags
mcp-securityagent-benchmarkingtool-poisoningruntime-evaluation
AI capabilities
TextStructured
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

Framework
FastAPI
Written with
Claude Code
Connectors
MCP
Runs on
CLISelf-hosted
Written with — evidence
Claude Code
commit 93fb82258be1 · since Oct 2026

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHub · ★ 1Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed2 Oct · 15:27 UTC
    mcp-guardbench seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about mcp-guardbench

What does mcp-guardbench do?
Inferred · not functionally tested: Mcp-guardbench focuses on evaluating and detecting security risks in Model Context Protocol tool-using agents. It is catalogued under Agent evaluation & testing on PulseGate.
Who is mcp-guardbench for?
Inferred · not functionally tested: mcp-guardbench is an open-source project built for AI security researchers and developers building MCP agents.
Does mcp-guardbench have a free plan?
Basis unknown · not verified: Yes — mcp-guardbench is open source under the MIT license and free to use.
What platforms does mcp-guardbench run on?
Basis unknown · not verified: mcp-guardbench runs on the command line. It can also be self-hosted.
Is mcp-guardbench still active?
PulseGate's liveness check found it on 2 Oct 2026. Its GitHub repository shows 9 commits in the last 90 days.
What projects are similar to mcp-guardbench?
Similar projects tracked by PulseGate include mcp-agent-guard, mcp-guardian-scan, and mcp-behaviour-guard.mcp-agent-guardmcp-guardian-scanmcp-behaviour-guard
Who develops mcp-guardbench?
mcp-guardbench is developed by Manish Maurya.
When did mcp-guardbench launch?
mcp-guardbench first shipped in 2026.

Similar projects

Closest matches by what these projects do