SourceRecall MCP Server
SourceRecall
SourceRecall 是一个自托管的仓库智能服务,专为 AI 编码助手设计。它将干净的 Git 工作树索引到 Qdrant 中,结合语义和词汇检索,通过独立的 Jetson NLP 服务对候选结果进行重排序,并通过 HTTP 和模型上下文协议(MCP)暴露结果。
该服务专为小型可信网络部署而设计,仓库数据必须保持在操作者的控制之下。
亮点
安全仓库隔离,统一管理根目录
基于干净提交的索引,包含文件、块、模型和模式溯源
权威性全量重建索引,移除过时的 Qdrant 点
混合向量与 ripgrep 检索,结合块感知的倒数排位融合
通过 Jetson NLP 提供可选交叉编码器重排序
精简的流式 HTTP MCP 集成,支持结构化工具响应
持久化 SQLite 任务与索引状态
经过验证的 YAML 配置与结构化轮转日志文件
单工作线程、序列化索引模型,具有明确资源限制
Related MCP server: Claude Context MCP
架构
Continue Agent
|
| Streamable HTTP MCP
v
SourceRecall MCP :8071
|
v
SourceRecall API :8070
| |
| +--> managed Git repositories
| + ripgrep lexical retrieval
|
+--> Qdrant :6333
+--> Jetson NLP :8091 (/v1/embeddings and /v1/rerank)SourceRecall 负责仓库、路径、提交、块和检索语义。Jetson NLP 仍然是一个无状态推理服务,仅处理文本、向量和分数。
仓库布局
config/ Versioned configuration template
deploy/systemd/ API and MCP systemd units
diags/ Deployment validation utilities
docs/ Architecture, API, deployment, and operations guides
src/source_recall/ Installable Python package
tests/ Automated testsAPI 概览
curl http://source-recall:8070/live
curl -X POST http://source-recall:8070/index \
-H 'Content-Type: application/json' \
-d '{"repository":"episode-tracker"}'
curl -X POST http://source-recall:8070/search \
-H 'Content-Type: application/json' \
-d '{
"repository":"episode-tracker",
"query":"where are TV episode credits normalized?",
"limit":8
}'当配置了 security.api_token 时,请在所有非健康检查的 API 请求中添加 Authorization: Bearer <token>。
生产路径
用途 | 路径 |
应用程序 |
|
虚拟环境 |
|
配置文件 |
|
受管仓库 |
|
持久化状态 |
|
应用日志 |
|
API 服务 |
|
MCP 服务 |
|
完整安装流程请参见 部署。
文档
当前范围
初始版本执行权威性全量索引。增量 Git 索引、Webhook 接入、语法感知分块、符号图及引用分析属于计划中的扩展功能,而非当前声称的特性。索引任务具有持久化状态报告能力,但在单个本地进程中执行;这不是一个分布式任务队列。
服务不终止 TLS,MCP 端点也不实现客户端认证。请将其部署在可信的私有网络中,或置于经过认证的反向代理之后。参见 安全。
许可证
SourceRecall 采用 MIT 许可证。
This 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-quality-maintenanceProvides AI-powered semantic code search across multiple repositories, allowing natural language queries to find code chunks and retrieve specific file contents through Dolphin AI embeddings.42
- Flicense-qualityDmaintenanceEnables AI assistants to index and search codebases using semantic search powered by multiple embedding providers (OpenAI, VoyageAI, Gemini, Ollama) and vector database storage.
- Alicense-qualityDmaintenanceEnables AI coding assistants to search and retrieve information from a locally ingested knowledge base using hybrid search, grounded in user-curated documentation.17MIT
- Alicense-qualityDmaintenanceEnables AI assistants to perform intelligent semantic code search across codebases using local AI embeddings for meaning-based retrieval.56MIT
Related MCP Connectors
Search your knowledge bases from any AI assistant using hybrid RAG.
Enterprise code intelligence for M&A, security audits, and tech debt. Hosted server with 200k free.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
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/Mortau/source-recall'
If you have feedback or need assistance with the MCP directory API, please join our Discord server