github Python analyzed 224f09d

cognis-digital/codegraph-mcp

github

No-train, on-prem code knowledge graph served to AI agents over MCP, with a hash-chained audit row for every read.

maintainer
cognis-digital
licence
NOASSERTION
first seen
2026-06-28
last seen
2026-06-30
releases · 30d
0
short id

cognis-digital/codegraph-mcp is an MCP server distributed on github, maintained by cognis-digital, tracked here since June 2026. It has shipped 1 release and exposes 11 tools. Tools include cross_language_edges, find_callees, find_callers, find_hotspots, find_orphans, find_references, and 5 more. Its composite risk grade is A — an inferred review prompt computed from observed signals, not a verdict.

what we found

Reading the source raised one review prompt — exfiltration combo — each a pattern worth a human look rather than a finding of fault.

Its 11 tools appear to reach filesystem and network, inferred from tool names, descriptions and input schemas rather than from observed behaviour.

Since the previous scan on 2026-08-26: 3 tools added.

full security breakdown →
tools 11
  • cross_language_edges All resolved cross-language HTTP edges.
  • find_callees What a symbol calls.
  • find_callers Direct callers of a symbol — includes cross-language edges.
  • find_hotspots Most depended-on symbols (highest caller count) — where changes ripple furthest.
  • find_orphans Dead-code candidates: functions/methods with no callers and not HTTP entrypoints.
  • find_references Every call site / use of a name.
  • get_symbol Full record for one symbol id (signature, location, container).
  • graph_stats File / symbol / edge / language counts.
  • impact_analysis Transitive callers — the blast radius of a change.
  • project_graph Module/package-level dependency graph — the architecture map above the symbols.
  • search_symbols Find symbols by name substring (optionally filter by kind).
release cadence · 90d 1 releases
06-14 00:00 07-28 00:00 now
recent releases last 1
version date src
walkthrough-v1 2026-06-30 github

view all →