RFP.ai
v1.0.1
ai.rfp/rfp-ai
Draft cited RFP and security questionnaire answers from your knowledge base, with human review
io.github.achreftlili/code-index · v1.0.6
SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.
Code Index 是一个MCP Server,收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。
选择你的平台查看安装方式
{
"mcpServers": {
"code-index": {
"command": "uvx",
"args": [
"mcp-code-index"
]
}
}
}CODE_INDEX_EMBEDDER可选Embedder backend. Only 'jina' (local jina-embeddings-v2-base-code via sentence-transformers) is supported; the variable exists for future expansion.
CODE_INDEX_EMBED_MODEL可选HuggingFace model id. Defaults to 'jinaai/jina-embeddings-v2-base-code'. Override only if you know the model is dim-compatible.
CODE_INDEX_EMBED_DIM可选Embedding dimension. Defaults to 768 (matches jina-embeddings-v2-base-code). Must match the model's output dim.
CODE_INDEX_DB可选Path to the SQLite index database. Defaults to .claude/index.db relative to the working directory.
CODE_INDEX_EMBED_BATCH可选Encode batch size (default 32). Lower (e.g. 8 or 4) to reduce peak memory if the GPU OOMs on large files.
CODE_INDEX_EMBED_DEVICE可选Torch device override: 'cpu', 'mps', or 'cuda'. Unset = auto-detect. Set 'cpu' to avoid Apple-Silicon MPS out-of-memory errors.
v1.0.1
ai.rfp/rfp-ai
Draft cited RFP and security questionnaire answers from your knowledge base, with human review
v1.1.0
io.github.xenarch-ai/xenarch-mcp
Xenarch — x402 MCP server for AI agent payments. Non-custodial, USDC on Base L2.
v1.0.0
com.docimprint/api
AI document intelligence: extract, summarize, claim-check, and notarize with on-chain proofs.
v0.14.0
io.github.blackwell-systems/agent-lsp
Stateful LSP runtime for AI agents — 50+ tools across 30+ languages via MCP.
v0.2.13
io.github.hostinger/hostinger-api-mcp
MCP server for Hostinger API
v0.41.0
io.github.zhitongblog/unterm
The terminal AI agents can drive: spawn panes, run commands, read screens, scrolling screenshots.
{
"id": "io.github.achreftlili/code-index",
"type": "mcp-server",
"version": "1.0.6",
"displayName": "Code Index",
"description": "SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.",
"repository": {
"url": "https://github.com/achreftlili/code-index",
"source": "github"
},
"distribution": {
"packages": [
{
"registryType": "pypi",
"identifier": "mcp-code-index",
"version": "1.0.6",
"transport": "stdio",
"environmentVariables": [
{
"name": "CODE_INDEX_EMBEDDER",
"description": "Embedder backend. Only 'jina' (local jina-embeddings-v2-base-code via sentence-transformers) is supported; the variable exists for future expansion."
},
{
"name": "CODE_INDEX_EMBED_MODEL",
"description": "HuggingFace model id. Defaults to 'jinaai/jina-embeddings-v2-base-code'. Override only if you know the model is dim-compatible."
},
{
"name": "CODE_INDEX_EMBED_DIM",
"description": "Embedding dimension. Defaults to 768 (matches jina-embeddings-v2-base-code). Must match the model's output dim."
},
{
"name": "CODE_INDEX_DB",
"description": "Path to the SQLite index database. Defaults to .claude/index.db relative to the working directory."
},
{
"name": "CODE_INDEX_EMBED_BATCH",
"description": "Encode batch size (default 32). Lower (e.g. 8 or 4) to reduce peak memory if the GPU OOMs on large files."
},
{
"name": "CODE_INDEX_EMBED_DEVICE",
"description": "Torch device override: 'cpu', 'mps', or 'cuda'. Unset = auto-detect. Set 'cpu' to avoid Apple-Silicon MPS out-of-memory errors."
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.achreftlili/code-index",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.achreftlili%2Fcode-index/versions/latest",
"isOfficial": true,
"status": "active"
}
}