Is the toolfence MCP server actively maintained?

The toolfence MCP server was last committed 2mo ago and has 1 contributor. Issue health: 50% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

toolfence MCP Server

Name: jiangkoumo/toolfence
Rating: 3.1 (1 reviews)
Author: jiangkoumo

jiangkoumo/toolfence

Score: 51.3 Rank #16697 MCP Server

[![AgentRank](https://agentrank-ai.com/api/v1/badge/jiangkoumo--toolfence)](https://agentrank-ai.com/tool/jiangkoumo--toolfence/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of jiangkoumo/toolfence? Claim this listing →

Local, fail-closed policy enforcement and human approval for MCP tool calls.

Add AgentRank to Claude Code Discover and compare tools like jiangkoumo/toolfence — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

jiangkoumo/toolfence is a TypeScript tool licensed under MIT. Local, fail-closed policy enforcement and human approval for MCP tool calls. Topics: ai-agents, mcp, policy, proxy, security.

Ranked #16697 out of 24846 indexed tools.

Ecosystem

TypeScript MIT

ai-agentsmcppolicyproxysecurity

Score Breakdown

Stars 15% 100

100 stars → early stage

Freshness 25% 2mo ago

Last commit 2mo ago → moderate activity

Issue Health 25% 50%

No issues filed → no history to score

Contributors 10% 1

1 contributor → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 0

Description Good

License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 65 days ago — a recent commit would boost your freshness score

Contributors medium impact

Single-contributor projects carry bus-factor risk — welcoming contributors boosts confidence

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/jiangkoumo--toolfence)](https://agentrank-ai.com/tool/jiangkoumo--toolfence/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/jiangkoumo--toolfence/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/jiangkoumo--toolfence" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="jiangkoumo/toolfence"></script>

Details

Stars: 100
Forks: 0
Open Issues: 0
Closed Issues: 0
Contributors: 1
Dependents: —
Language: TypeScript
License: MIT
Last Commit: 2mo ago

Matched Queries

topic:mcp

From the README

# ToolFence

**A vendor-neutral policy firewall for MCP tool calls.**

ToolFence enforces one testable least-privilege policy between AI agents and stdio MCP servers. With a conservative default (`ask` or `deny`), the same rules can be used from Codex, Cursor, or Claude Desktop: safe calls pass, dangerous or unrecognized calls stop before upstream execution, and uncertain calls require human approval—without changing the MCP host or server.

- **Portable policy:** keep resource and command rules independent of a single Agent platform.
- **Deterministic enforcement:** normalize tool calls, give `deny` precedence, and surface unknown or ambiguous actions for conservative policy handling.
- **Auditable evidence:** record privacy-conscious decisions and result hashes without storing raw arguments or results.

## Same MCP call. Different outcome.

The animation sends the same `.env` read to the official Filesystem MCP Server twice:

- without ToolFence, the server returns the explicitly syn

Read full README on GitHub →