@coderule/mcp 1.7.0 → 1.7.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/dist/mcp-cli.js CHANGED
@@ -1929,13 +1929,7 @@ function createMcpServer({
1929
1929
  "check",
1930
1930
  {
1931
1931
  title: "Coderule Indexing Status",
1932
- description: `Check the current state of the code indexer. Returns repository info, file states (clean/dirty/hashing/missing), queue metrics, latest snapshot details, and service health.
1933
-
1934
- Use this tool to:
1935
- - Debug why queries are failing or returning no results
1936
- - Verify the indexer is ready before querying
1937
- - Check which repository is currently indexed
1938
- - Monitor indexing progress`,
1932
+ description: "Check the current state of the code indexer. Returns repository info, file states, queue metrics, snapshot details, and service health. Use to debug query failures or verify indexer readiness.",
1939
1933
  inputSchema: {},
1940
1934
  annotations: {
1941
1935
  readOnlyHint: true,
@@ -1956,40 +1950,36 @@ Use this tool to:
1956
1950
  "query",
1957
1951
  {
1958
1952
  title: "Semantic Code Retrieval",
1959
- description: `Graph-based RAG for semantic code search across the indexed codebase.
1960
-
1961
- \u{1F6A8} CRITICAL: Use this tool FIRST before any code modification, bug fix, feature addition, or architecture exploration.
1953
+ description: "\u{1F6A8} CRITICAL: ALWAYS use this tool FIRST before any code modification, bug fix, feature addition, or architecture exploration. Graph-based RAG for semantic code search using AST relationships and embeddings. Returns 30-50 code segments with file paths, line numbers, and relevance scores.",
1954
+ inputSchema: {
1955
+ query: z.string().min(1, "Query text is required").describe(`Keyword-rich query using technical terms (NOT natural language questions).
1962
1956
 
1963
- QUERY STRATEGY:
1964
- Use keyword-rich technical terms, NOT natural language questions.
1957
+ STRATEGY: Use space-separated technical keywords that describe what you're looking for.
1965
1958
 
1966
- \u2705 GOOD: "JWT authentication middleware token validation security handler FastAPI"
1967
- \u2705 GOOD: "file indexing worker celery queue job AST parser embedding chunker"
1968
- \u2705 GOOD: "database schema SQLAlchemy model migration table column relationship"
1959
+ \u2705 GOOD EXAMPLES:
1960
+ - "JWT authentication middleware token validation security handler FastAPI"
1961
+ - "file indexing worker celery queue job AST parser embedding chunker"
1962
+ - "database schema SQLAlchemy model migration table column relationship"
1963
+ - "error handling exception try catch logging traceback"
1969
1964
 
1970
- \u274C BAD: "How does authentication work?"
1971
- \u274C BAD: "Show me the login code"
1965
+ \u274C BAD EXAMPLES:
1966
+ - "How does authentication work?" (natural language question)
1967
+ - "Show me the login code" (conversational)
1968
+ - "auth" (too vague, needs more context)
1972
1969
 
1973
1970
  RETRIEVAL MECHANISM:
1974
- - Seeds: Semantic similarity via embeddings (~6 initial matches)
1975
- - Flood: Graph propagation through AST relationships (imports, calls, inheritance)
1976
- - Neighbors: Adjacent code chunks for context
1977
- - Calls: Function call relationships
1971
+ Combines multiple strategies: Seeds (semantic similarity), Flood (AST graph propagation through imports/calls/inheritance), Neighbors (adjacent chunks), and Calls (function relationships).
1978
1972
 
1979
- Returns 30-50 code segments with file paths, line numbers, and relevance scores.
1980
-
1981
- DEFAULT BUDGET: 10,000 tokens (sufficient for most tasks)
1982
-
1983
- WHEN TO USE:
1973
+ WHEN TO USE THIS TOOL:
1984
1974
  - Before modifying ANY existing code
1985
1975
  - Understanding system architecture
1986
- - Finding related implementations
1987
- - Locating tests or examples
1976
+ - Finding related implementations or patterns
1977
+ - Locating tests or usage examples
1988
1978
  - Bug investigation
1989
- - Feature implementation planning`,
1990
- inputSchema: {
1991
- query: z.string().min(1, "Query text is required"),
1992
- budgetTokens: z.number().int().positive().optional().describe("Token budget for retrieval (default 10000)")
1979
+ - Feature implementation planning`),
1980
+ budgetTokens: z.number().int().positive().optional().describe(
1981
+ "Token budget for retrieval results. Default: 10000. Range: 1000-20000. Higher budgets return more context but use more tokens. 10k is sufficient for most tasks."
1982
+ )
1993
1983
  },
1994
1984
  annotations: {
1995
1985
  readOnlyHint: true,