StackMap
Subscribe

cocoindex-code vs codegraph-mcp

AST-based semantic code search for coding agents: pipx install, zero config, local embeddings out of the box — a CLI/skill/MCP that cuts agent context ~70% vs grepping. Built on CocoIndex. — versus — No-train, on-prem code knowledge graph served to AI agents over MCP — symbols, call edges, cross-language links and blast-radius queries, with a hash-chained audit log of every read.

The curated verdict

Both serve codebase context to agents over MCP. codegraph-mcp builds a cross-language knowledge graph with audit logging for on-prem rigor; cocoindex-code trades graph depth for zero-config semantic search that installs in a minute.

cocoindex-codecodegraph-mcp
Stars2.5k5
Forks2030
LanguagePythonPython
LicenseApache-2.0NOASSERTION
Last activity4 days ago18 days ago
Topicscoding, localcoding, rag
Curated connections37

cocoindex-code — the curator's take

The lowest-friction entry in the code-context-server category: one pipx install, zero config, and the [full] variant ships local embeddings so there's no API key before first search. AST-aware chunking plus the CocoIndex engine underneath means the index stays fresh incrementally instead of rebuilding. Integrates as a skill or MCP with Claude Code, Codex, Cursor. NOT the deepest graph: it's semantic search, not call-graph analysis — no callers/blast-radius queries (that's TokenSave or codegraph-mcp territory) — and the slim install quietly requires a cloud embedding key while [full] costs ~1GB of torch.

codegraph-mcp — the curator's take

Niche but real: if agents must understand code that cannot leave your building AND compliance asks 'what exactly did the agent read', the tamper-evident audit chain is the only game in town; cross-language call edges (TS fetch → Go/Python handler) catch what one-file context misses. NOT for most teams yet: 5 stars, single vendor, and — deal-breaker until fixed — no clear open-source license (NOASSERTION on GitHub). Treat it as an evaluation candidate, not a dependency.