intelligraph-mini
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@intelligraph-mini find the shortest path from ConfigManager to Database"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Intelligraph-mini
Local-first MCP graph intelligence server — same RRF hybrid search, multi-hop traversal, source snippets, and rationale nodes as the full Intelligraph platform, but without Docker, web UI, SSO, or chat. Just tools for your AI agent.
Need the full platform? Intelligraph adds Docker, React web UI, chat completions, SSO/PKCE, closed-network deployment, and tuning controls.
Quick start
pip install intelligraph-mini
# In your project directory:
intelligraph-mini --repo-dir .
# Or with MCP config (.mcp.json):
{
"mcpServers": {
"intelligraph-mini": {
"command": "intelligraph-mini",
"args": ["--repo-dir", "."]
}
}
}First run builds graphify + CRG indexes (~60s). Subsequent runs load cached (~2s). The bundled all-MiniLM-L6-v2 model (87MB) works fully offline — no API calls, no network.
Related MCP server: corpus-rag
Tools
Tool | Description |
| RRF hybrid search (FTS5 + semantic embeddings). Finds symbols by meaning. |
| Multi-hop subgraph + source code snippets + rationale notes. |
| Shortest path between two symbols in the call graph. |
| Blast-radius analysis over CALLS/IMPORTS_FROM edges. |
| Read source files from disk. |
How it works
Build (first run):
graphify update .+code-review-graph build→graphify-out/graph.json+.code-review-graph/graph.dbSnippets: reads source files, stores ~500 char snippets per node in
node_snippetstableSearch: RRF (Reciprocal Rank Fusion, k=30) blends FTS5 keyword ranking with embedding cosine similarity. Adaptive 50% cutoff returns only genuinely relevant files.
Traversal: BFS with token budget over cached adjacency (scales to 140k edges)
Rationale: surfaces
#NOTE/#WHYnodes from graphify's rationale extraction
Requirements
Python 3.10+
graphifyyandcode-review-graphCLIs on PATH (installed automatically as dependencies)
License
MIT
Available Tools
5 toolsimpactA
Complete blast radius of changing a symbol. Exhaustive traversal of ALL edge types. Returns every affected file with symbols to check. Use before refactoring. Files not listed do not depend on the target.
Inputs: name (required).
local_filesA
Read full source files from disk. EXPENSIVE. Prefer built-in Read with line ranges from search/node results instead. Use this only when you need a whole file that search/node didn't cover.
Inputs: paths (required), max_bytes.
nodeA
Get a symbol's connections (callers, callees, imports) with file:line ranges. Use AFTER search. Then use built-in Read with those line ranges to get implementation details. Replaces reading whole files — read only the specific line ranges shown.
Inputs: name (required), depth.
pathC
Trace the shortest path between two symbols in the codebase graph.
Inputs: to (required), from (required).
searchA
Search the codebase for symbols, files, or concepts. Works equally well for exact names ('UserStatus'), file paths ('types/enums'), or natural language ('how authentication works'). Returns name, kind, file path with line ranges (file:start-end), and confidence [H/M/L]. Use built-in Read with offset=line_start, limit=line_end-line_start to get source. Use this FIRST — replaces grep and glob.
Inputs: query (required), near.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct role: search locates symbols, node shows connections, path finds shortest routes, impact assesses blast radius, and local_files reads source. No two tools overlap in purpose.
Names are mostly single-word and lowercase, but mix verbs (search) and nouns (node, path, impact, local_files). The underscore in local_files is inconsistent with the other names, though still readable.
Five tools is well-scoped for a mini code-graph intelligence server, covering search, exploration, pathfinding, impact analysis, and file reading without redundancy.
The set covers the full analysis workflow: locate, explore, trace, assess, and read. Instructions to use built-in Read with line ranges fill any need for source access, leaving no obvious gaps.
Related MCP Connectors
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceLocal MCP server for indexing personal knowledge into SQLite with hybrid search, chunk-level citations, memory tools, and agent orchestration.4MIT
- AlicenseNot gradedqualityBmaintenanceMCP server for local RAG over personal notes, PDFs, and documents, enabling plain-English querying and hybrid search with multi-hop context expansion.MIT
- AlicenseAqualityDmaintenanceA local MCP server enabling hybrid search over documents, memory, and knowledge graphs for retrieval-augmented generation, with tools for SQLite, semantic memory, and entity-relationship queries.41MIT
- AlicenseBqualityBmaintenanceZero-trust, air-gapped Enterprise GraphRAG MCP server. Build knowledge graphs from local documents and run multi-hop, citation-grounded queries entirely offline with Ollama.1730 PyPI326MIT