Skip to main content
Glama

fastroute

本地 MCP 插件:agent 接到新任务时,从本地已安装的全部 skill(用户级/插件级/项目级)中检索 Top-N 推荐。只推荐不执行。

索引方法来自 SkillRouter(arXiv 2603.22455):all-field 分段多向量(name+description 一个向量 + 正文 ~800 字符切块各一个向量),查询对每块算余弦、skill 得分取 max-pool。

工具

工具

用途

recommend_skills

任务开始前检索最相关 skill;返回 score、tier(auto/prompt/skip,参考值)、调用名与路径

reindex_skills

安装/删除 skill 后增量重建索引(mtime diff),无需重启会话

Related MCP server: skills-mcp-server

安装(Claude Code)

claude mcp add fastroute -- node /absolute/path/to/fastroute/dist/index.js

数据与模型

  • 数据目录 ~/.fastroute(FASTROUTE_DATA_DIR 覆盖):fastroute.db、config.json、models/

  • embedding 模型:Xenova/paraphrase-multilingual-MiniLM-L12-v2(q8,约 135MB),首次调用工具时联网下载,默认 ModelScope 镜像(FASTROUTE_EMBEDDING_HOST 可指回 https://huggingface.co);已有 ~/.knowyoubetter/models 缓存时直接复用

  • 模型是硬依赖:离线且无缓存时工具返回错误与下载指引,无词法降级

  • config.json 可覆盖:chunkSize(800)、autoThreshold(0.9)、promptThreshold(0.6)、topK(5)、userSkillsDir、pluginCacheDir、projectSkillsEnabled

  • 修改 chunkSize 后已有索引不会自动重切:需删除 ~/.fastroute/fastroute.db 再调用 reindex_skills

开发

npm install
npm test            # 单测 + 集成(fake embedder,不联网)
npm run test:real   # 真实 embedding 冒烟(首次下载模型)
npm run eval        # distractor 评测:Hit@1/Hit@5/MRR
npm run build
npx @modelcontextprotocol/inspector node dist/index.js

Related MCP Connectors

  • Search and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.

  • The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.

  • Fastio gives your team and AI agents a workspace for each project, bringing source files, comments and new work together. Connect a compatible MCP client to find files, answer questions from project material, and save results where the team can review and use them. \ Sign in through Fastio and choose the workspaces the connection can reach. Read Only connections expose read tools; Read & Write connections also allow changes. \ • **Files and folders:** browse, read, upload, and organize files, with version history and trash. • **Search:** find files by keyword; search file content and meaning when Deep Indexing is enabled and files have been processed. • **Metadata:** read, set, and search metadata fields, including extracted fields where available. • **Shares:** create and manage shares for sending or collecting files. • **Comments and members:** read and add comments, and manage workspace membership within your permissions. • **Activity:** search workspace events to see what changed. \ Hosted by Fastio, with no server installation required. \ • **Claude and most MCP clients:** https://mcp.fast.io/mcp/tools • **ChatGPT:** https://mcp.fast.io/mcp/operations • **ChatGPT and Codex:** Fastio plugin • **Claude Code, Cursor and similar coding agents:** https://mcp.fast.io/mcp/code • **Setup and client-specific capabilities:** https://mcp.fast.io/docs \ Paid plans. Monthly plans include a trial of up to 30 days. A card is required, and billing begins when the trial ends or trial credits run out, whichever comes first. No free plan.

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    FastMCP is a comprehensive MCP server allowing secure and standardized data and functionality exposure to LLM applications, offering resources, tools, and prompt management for efficient LLM interactions.
    3
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A high-performance MCP server that provides BM25-ranked search and structured access to over 1,300 AI skills, enabling context-efficient discovery and usage of AI capabilities while minimizing token consumption.
    14 npm
    ISC
  • F
    license
    Not graded
    quality
    D
    maintenance
    A hierarchical MCP server for managing skill definitions with a browsable tree structure and full-text search. It allows AI agents to efficiently discover and use skills without consuming context tokens.
    -