Commit Graph
5 Commits
Author SHA1 Message Date
KaifAhmad1 62a027d6fd fix(mcp): call backend get_causal_chain only once on internal TypeError
Signature introspection and the resulting call were sharing one
try/except, so a genuine bug inside a backend's get_causal_chain
(raising an unrelated TypeError) was misread as a signature mismatch,
causing an identical retry call before the real error surfaced.
Split introspection from the call so a successfully-introspected call
happens exactly once; the trial-and-error cascade now only runs when
inspect.signature itself fails. Also adds the CHANGELOG entry for
#781/#817, which was missing.
2026-07-31 13:14:29 +05:30
Sameer6305 a1f835c9b2 refactor(mcp): harden handle_get_causal_chain inputs and signature introspection (#781)
- Add safe input validation and bounds clamping on max_depth (1..100) to prevent DoS/memory exhaustion

- Use inspect.signature for accurate keyword dispatch with precise TypeError fallback

- Prevent masking of genuine internal TypeError exceptions inside graph backends

- Add security and input hardening regression tests
2026-07-30 19:09:22 +05:30
Sameer6305 12172d03b4 fix(mcp): fixed qodo reviews (#781)
- Support legacy (depth kwarg) and positional-only get_causal_chain backend signatures in fallback path

- Add regression tests for signature compatibility
2026-07-30 19:04:00 +05:30
Sameer6305 60f362817f fix(mcp): return error when causal chain analysis unsupported (#781)
- Return explicit error dictionary when graph lacks get_causal_chain instead of silent empty list

- Forward direction and max_depth in fallback graph.get_causal_chain call

- Add regression tests for error signaling and parameter forwarding
2026-07-30 18:11:04 +05:30
KaifAhmad1andClaude Sonnet 4.6 7b31304e1e feat(mcp): add modular MCP server package at repo root
Adds a fully self-contained `mcp/` package that exposes Semantica as a
Model Context Protocol server over stdio (JSON-RPC 2.0).

17 tools across 5 domains:
- Extraction: extract_entities, extract_relations, extract_all
- Decision intelligence: record_decision, query_decisions, find_precedents,
  get_causal_chain, analyze_decision_impact
- Knowledge graph: add_entity, add_relationship, search_graph,
  get_graph_summary, get_graph_analytics
- Reasoning: run_reasoning, abductive_reasoning
- Export & provenance: export_graph (JSON/CSV/GraphML/Parquet/RDF), get_provenance

4 resources: semantica://graph/summary, semantica://decisions/list,
semantica://schema/info, semantica://ontology/schema

Package layout:
  mcp/__init__.py + __main__.py  — entry points (python -m mcp)
  mcp/server.py                  — SemanticaMCPServer + stdio event loop
  mcp/session.py                 — lazy ContextGraph singleton
  mcp/schemas.py                 — JSON Schema for all 17 tool inputs
  mcp/tools/{extraction,decisions,graph,reasoning,export}.py
  mcp/resources/registry.py      — URI → handler map
  mcp/README.md                  — per-tool setup (Claude Code, Cursor, Windsurf,
                                   Cline, Continue, VS Code, Amazon Q)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-13 17:38:23 +05:30