Skip to main content
Glama
deenesjakoruzh
swnotmetal

koma-gate-mcp

by swnotmetal
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

Koma Gate MCP

将 Koma Gate 的提示注入分类功能作为 MCP 工具暴露给 AI 代理。

npm install koma-gate-mcp

功能

提供一个名为 classify_input 的单一工具，AI 代理可以调用该工具来检查不受信任的用户文本是否安全且在作用域内，然后再对其执行操作。

Related MCP server: agent immune

设置

设置提供商和 API 密钥：

# Provider: openai | anthropic | google | deepseek | ollama (default: google)
export KOMA_PROVIDER=google
export GEMINI_API_KEY=sk-...

Claude Desktop

添加到 claude_desktop_config.json：

{
  "mcpServers": {
    "koma-gate": {
      "command": "npx",
      "args": ["-y", "koma-gate-mcp"]
    }
  }
}

工具：classify_input

  • text（必需）——要分类的不受信任的用户输入

  • preset（可选）——general | code | support | reference（默认：general）

返回：

{
  "allowed": true,
  "in_scope": true,
  "reason": "in scope",
  "preset": "general",
  "model": "gemini-2.5-flash"
}

安全边界

这是一个基于 LLM 的作用域分类器，而非加密级别的提示注入防御。有关完整的安全边界，请参阅 koma-gate 的 README；有关评估结果，请参阅 BENCHMARKS.md。

This server cannot be installed

A
license - permissive license
-
quality - not tested
A
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
3dRelease cycle
3Releases (12mo)
Commit activity
Issues opened vs closed

Resources

Related MCP Servers

  • mcp-safe-proxy

    Huan-zhaojun
    A
    license
    -
    quality
    D
    maintenance
    A lightweight stdio proxy that intercepts and rewrites MCP tool annotations to bypass security approval prompts in AI CLIs like Codex and Claude Code. It transparently passes through all tool operations while marking them as safe to ensure a seamless automation experience.
    11
    10
    MIT

  • agent immune

    denial-web
    A
    license
    -
    quality
    C
    maintenance
    Adaptive security for AI agents: assess inputs for prompt injection, scan outputs for credential/PII leaks, teach new attack patterns to semantic memory, harden prompts, and monitor metrics. Runs locally via MCP stdio.
    Apache 2.0
  • jamjet-policy by jamjet-labs

    jamjet-policyofficial

    jamjet-labs
    A
    license
    A
    quality
    B
    maintenance
    Drop-in stdio interceptor that gates MCP tools/call requests through a YAML policy (block / require_approval / audit / budget cap) before they reach the real server. The same policy file is reused by @jamjet/claude-code-hook and @jamjet/openai-guardrail, so one rule set covers Claude Desktop, Cursor, OpenAI Agents, and custom clients.
    3
    2
    Apache 2.0
  • Blekline MCP Server by Blekline

    Blekline MCP Serverofficial

    Blekline
    A
    license
    A
    quality
    A
    maintenance
    Provides AI ingress governance by masking prompts, classifying risk, and enforcing tool policies before agent calls reach model providers or sandboxes.
    6
    1
    AGPL 3.0

View all related MCP servers

Related MCP Connectors

  • agent-prompt-injection-firewall-mcp

    The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...

  • sigma-gate

    Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.

  • Prompt Compass

    Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/swnotmetal/Project-Koma'

If you have feedback or need assistance with the MCP directory API, please join our Discord server