fetch_spec

Instructions

Implementation Reference

• src/mk_spec_master/tools/specs.py:93-99 (handler)

  The actual tool handler for fetch_spec. Gets spec_id from arguments, calls source.fetch() via the active adapter, and returns the full Spec record as a dict.

  def fetch_spec_tool(arguments: dict) -> dict[str, Any]:
      spec_id = arguments.get("spec_id") or arguments.get("id")
      if not spec_id:
          return {"error": "spec_id is required"}
      source = get_source(SOURCE_NAME)
      spec = source.fetch(str(spec_id))
      return asdict(spec)

• src/mk_spec_master/server.py:44-63 (registration)

  The dispatch table that maps the string "fetch_spec" to the fetch_spec_tool handler function.

  _DISPATCH: dict[str, Callable[[dict], dict]] = {
      "get_spec_source_info": _meta_info,
      "list_specs": specs_tools.list_specs_tool,
      "fetch_spec": specs_tools.fetch_spec_tool,
      "parse_spec": specs_tools.parse_spec_tool,
      "extract_scenarios": scenarios_tools.extract_scenarios_tool,
      "generate_test_plan": scenarios_tools.generate_test_plan_tool,
      "link_test_to_spec": coverage_tools.link_test_to_spec_tool,
      "get_coverage_matrix": coverage_tools.get_coverage_matrix_tool,
      "get_drift_report": coverage_tools.get_drift_report_tool,
      "analyze_spec_quality": quality_tools.analyze_spec_quality_tool,
      "propose_spec_improvements": quality_tools.propose_spec_improvements_tool,
      "auto_link_tests": auto_link_tools.auto_link_tests_tool,
      "get_optimization_plan": optimization_tools.get_optimization_plan_tool,
      "init_spec_knowledge": spec_knowledge_tools.init_spec_knowledge_tool,
      "get_spec_context": spec_knowledge_tools.get_spec_context_tool,
      "get_spec_history": history_tools.get_spec_history_tool,
      "get_drift_signature": history_tools.get_drift_signature_tool,
      "get_telemetry": telemetry_tools.get_telemetry_tool,
  }

• src/mk_spec_master/server.py:100-115 (schema)

  The MCP Tool registration for fetch_spec, including its description and inputSchema (requires spec_id string).

  Tool(
      name="fetch_spec",
      description=(
          "Pull a single spec by id from the active source. For markdown_local "
          "the id is either the `id:` field in frontmatter or the filename "
          "stem; for github_issues it's the issue number as string. Returns "
          "the full Spec record {id, title, body, url, status, labels, metadata}. "
          "Pair with parse_spec to extract structured acceptance criteria."
      ),
      inputSchema={
          "type": "object",
          "properties": {
              "spec_id": {"type": "string"},
          },
          "required": ["spec_id"],
      },

• src/mk_spec_master/adapters/__init__.py:16-21 (helper)

  The get_source function used by fetch_spec_tool to obtain the adapter instance for the active source.

  def get_source(name: str) -> SpecSource:
      if name not in REGISTRY:
          raise ValueError(
              f"Unknown SPEC_SOURCE={name!r}. Available: {sorted(REGISTRY)}"
          )
      return REGISTRY[name]()