fastroute
fastroute
로컬 MCP 플러그인: agent가 새 작업을 받으면 로컬에 설치된 모든 skill(사용자 레벨/플러그인 레벨/프로젝트 레벨)에서 Top-N 추천을 검색합니다. 추천만 하고 실행하지 않습니다.
인덱싱 방법은 SkillRouter(arXiv 2603.22455)에서 가져왔습니다: all-field 분할 멀티벡터(name+description 하나의 벡터 + 본문 약 800자 청크 각각 하나의 벡터), 쿼리는 각 청크에 대해 코사인을 계산하고 skill 점수는 max-pool을 사용합니다.
도구
도구 | 용도 |
| 작업 시작 전 가장 관련성 높은 skill을 검색; score, tier(auto/prompt/skip, 참고값), 호출명과 경로를 반환 |
| skill 설치/삭제 후 인덱스를 증분 재구성(mtime diff), 세션 재시작 불필요 |
Related MCP server: skills-mcp-server
설치(Claude Code)
claude mcp add fastroute -- node /absolute/path/to/fastroute/dist/index.js데이터 및 모델
데이터 디렉터리
~/.fastroute(FASTROUTE_DATA_DIR로 재정의 가능):fastroute.db,config.json,models/embedding 모델:
Xenova/paraphrase-multilingual-MiniLM-L12-v2(q8, 약 135MB), 도구를 처음 호출할 때 인터넷에서 다운로드하며 기본적으로 ModelScope 미러(FASTROUTE_EMBEDDING_HOST로https://huggingface.co지정 가능)를 사용; 이미~/.knowyoubetter/models캐시가 있으면 바로 재사용모델은 필수 의존성: 오프라인이고 캐시가 없으면 도구는 오류와 다운로드 안내를 반환하며, 어휘 폴백 없음
config.json에서 재정의 가능:
chunkSize(800),autoThreshold(0.9),promptThreshold(0.6),topK(5),userSkillsDir,pluginCacheDir,projectSkillsEnabledchunkSize변경 후 기존 인덱스는 자동으로 다시 분할되지 않음:~/.fastroute/fastroute.db를 삭제한 다음reindex_skills를 호출해야 함
개발
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.jsThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceFastMCP 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.3MIT
- Alicense-qualityDmaintenanceA 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.20ISC
- AlicenseAqualityDmaintenanceA FastMCP server that helps users discover, browse, and install agent skills from curated GitHub collections, with support for adding new skill sources.51MIT
- Flicense-qualityBmaintenanceA 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.
Related MCP Connectors
A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.
Paid remote MCP for agent code search routing MCP, structured receipts, audit logs, and reviewer-rea
Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/akushonkamen/fastroute'
If you have feedback or need assistance with the MCP directory API, please join our Discord server