codegraph-mcp vs tokensave
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. — versus — Code-intelligence MCP server for coding agents — a pre-indexed semantic graph (libSQL + FTS5) they query instead of grepping: symbols, callers, impact radius in one call. 100% local, 50+ languages.
Same job — a code knowledge graph served to agents over MCP: codegraph-mcp bets on compliance (hash-chained audit of every read, cross-language HTTP edges); tokensave bets on breadth and token savings (50+ langs, 80+ tools, 12 agent integrations).
| codegraph-mcp | tokensave | |
|---|---|---|
| Stars | 5 | 440 |
| Forks | 0 | 38 |
| Language | Python | Rust |
| License | NOASSERTION | MIT |
| Last activity | 12 days ago | today |
| Topics | coding, rag | coding, local |
| Curated connections | 4 | 6 |
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.
tokensave — the curator's take
Use it to stop agents burning tokens on grep/glob/read exploration: one MCP call returns the symbols, relationships and snippets a task needs, and it's local (libSQL, no cloud). Broad reach — 50+ languages, 12+ agent integrations. NOT worth it on small repos where a couple of greps suffice, and it's an index you must keep fresh (re-index on change) — a stale graph misleads the agent. 80+ tools is a lot of surface; most tasks touch a handful.