proxysql

Commit Graph

Author	SHA1	Message	Date
Rene Cannao	acd05b60a9	Organize RAG test files properly - Move RAG test files to dedicated test/rag/ directory - Create proper Makefile in test/rag/ directory - Remove build_rag_test.sh script (replaced by Makefile) - Revert changes to main test/Makefile - Update documentation to reflect new test structure	3 months ago
Rahim Kanji	0d56918744	Add full-text search (FTS) tools to MCP query server Implement BM25-ranked full-text search capability for MySQL/MariaDB tables using SQLite-based external FTS index. Changes: - Add MySQL_FTS class for managing SQLite FTS indexes - Add FTS tools: fts_index_table, fts_search, fts_reindex, fts_delete_index, fts_list_indexes, fts_rebuild_all - Add thread-safe FTS lifecycle management with fts_lock mutex - Add reset_fts_path() for runtime FTS database path configuration - Add comprehensive FTS test scripts (test_mcp_fts.sh, test_mcp_fts_detailed.sh)	3 months ago
Rene Cannao	5d08deca7d	Fix AI agent review issues - Address SQL injection vulnerabilities by adding input validation and escaping - Fix configuration variable handling in get_variable and set_variable methods for RAG variables - Make embedding dimension configurable for rag_vec_chunks table - Remove code duplication in SQL filter building logic by creating consolidated build_sql_filters function - Update all search tools (FTS, vector, hybrid) to use consolidated filter building	3 months ago
Rene Cannao	ed65b6905b	Remove mistakenly created Doxygen files - Remove Doxyfile that was added by mistake - Remove .doxygen files from doc/ directory that were generated by mistake - Clean up documentation artifacts that shouldn't have been committed	3 months ago
Wazir Ahmed	e450f1b30f	MCP: Handle DELETE method - Respond with 405 Method Not Allowed, when clients send DELETE request for session termination. Signed-off-by: Wazir Ahmed <wazir@proxysql.com>	3 months ago
Wazir Ahmed	68a41d6db8	MCP: Add handler for prompts and resources Issue ----- - ProxySQL only supports the `tools` feature of the MCP protocol and does not support features such as `prompts` and `resources`. - Although ProxySQL expresses this in its `initialize` response, (server capabilities list contains only the `tools` object), clients such as Warp Terminal ignore it and continue to send requests for methods such `prompts/list` and `resources/list`. - Any response other than `HTTP 200 OK` is treated as an error and client fails to initialize. Fix --- - Handle prompt and resource list requests by returning an empty array. Signed-off-by: Wazir Ahmed <wazir@proxysql.com>	3 months ago
Wazir Ahmed	2f38def403	MCP: Handle client notifications properly - Fix incorrect method name for notification - Handle all notification messages in a generic way - Respond with HTTP 202 Accepted (no response body) Signed-off-by: Wazir Ahmed <wazir@proxysql.com>	3 months ago
Wazir Ahmed	155a77f969	MCP: Bump protocolVersion to 2025-06-18 - Version 2024-11-05 only supports HTTP_SSE as transport. - ProxySQL's MCP implemenation aligns more with the StreamableHTTP transport specified in version 2025-06-18. - Support for SSE in StreamableHTTP transport is optional. Signed-off-by: Wazir Ahmed <wazir@proxysql.com>	3 months ago
Rahim Kanji	bf429f0a52	Fixed multiple issues	3 months ago
Rene Cannao	a1d9d2f1ba	docs: Add comprehensive documentation to MCP features Add detailed function-level documentation to all MCP query rules, query digest, static harvester, and catalog components. Static_Harvester.cpp: - Document all 18+ harvest functions (schemas, objects, columns, indexes, FKs, views) - Document lifecycle methods (init, close, connect, disconnect) - Document helper methods (is_time_type, is_id_like_name) - Document run management (start_run, finish_run, run_full_harvest) - Document statistics methods (get_harvest_stats) Query_Tool_Handler.cpp: - Document JSON helper functions (json_string, json_int, json_double) - Document digest tracking section with flow explanation MySQL_Catalog.cpp: - Document schema isolation architecture - Document CRUD operations (upsert, get, search, list, remove, merge) Discovery_Schema.cpp: - Document MCP query rules evaluation (evaluate_mcp_query_rules) - Document digest functions (compute_mcp_digest, fingerprint_mcp_args) - Document update/get functions for rules and digests ProxySQL_Admin_Stats.cpp: - Document stats collection functions ProxySQL_Admin.cpp: - Document load/save functions for query rules Admin_Handler.cpp: - Document MCP query rules command handlers include/ProxySQL_Admin_Tables_Definitions.h: - Add comments explaining table purposes	3 months ago
Rene Cannao	ad166c6b8a	docs: Add comprehensive Doxygen documentation for RAG subsystem - Enhanced inline Doxygen comments in RAG_Tool_Handler.h and RAG_Tool_Handler.cpp - Added detailed parameter descriptions, return values, and cross-references - Created Doxyfile for documentation generation - Added documentation summary and guidelines - Documented all RAG tools with their schemas and usage patterns - Added security and performance considerations documentation The RAG subsystem is now fully documented with comprehensive Doxygen comments that provide clear guidance for developers working with the codebase.	3 months ago
Rene Cannao	55715ecc4b	feat: Complete RAG implementation according to blueprint specifications - Fully implemented rag.search_hybrid tool with both fuse and fts_then_vec modes - Added complete filter support across all search tools (source_ids, source_names, doc_ids, post_type_ids, tags_any, tags_all, created_after, created_before, min_score) - Implemented proper score normalization (higher is better) for all search modes - Updated all tool schemas to match blueprint specifications exactly - Added metadata inclusion in search results - Implemented Reciprocal Rank Fusion (RRF) scoring for hybrid search - Enhanced error handling and input validation - Added debug information for hybrid search ranking - Updated documentation and created completion summary This completes the v0 RAG implementation according to the blueprint requirements.	3 months ago
Rene Cannao	c092fdbd3b	fix: Load re_modifiers field from database in load_mcp_query_rules() Previously re_modifiers was hardcoded to 1 (CASELESS), ignoring the value stored in the database. Now properly reads from row->fields[7].	3 months ago
Rene Cannao	cc3cc25532	fix: Remove unused reset parameter from stats___mcp_query_rules() Change function signature from stats___mcp_query_rules(bool reset) to stats___mcp_query_rules() to match MySQL query rules pattern. The reset parameter was never used in the function body and MySQL's stats___mysql_query_rules() has no reset parameter.	3 months ago
Rene Cannao	8c9aecce9b	feat: Add LOAD MCP QUERY RULES FROM DISK / TO MEMORY commands - Add LOAD MCP QUERY RULES FROM DISK command - Add LOAD MCP QUERY RULES TO MEMORY command - Both commands copy rules from disk.mcp_query_rules to main.mcp_query_rules This completes the full set of MCP query rules LOAD/SAVE commands, matching the MySQL query rules pattern.	3 months ago
Rene Cannao	7e6f9f0ab3	fix: Add MCP query rules LOAD/SAVE command handlers - Add separate MCP QUERY RULES command block in Admin_Handler - Fix string length comparison (21 chars for "SAVE/LOAD MCP QUERY RULES ") - Add handlers for: - LOAD MCP QUERY RULES TO RUNTIME - SAVE MCP QUERY RULES TO DISK - SAVE MCP QUERY RULES TO MEMORY / FROM RUNTIME - Register mcp_query_rules in disk database (tables_defs_config) Previously MCP commands were incorrectly nested inside MYSQL/PGSQL block and could not be reached. Now they have their own conditional block.	3 months ago
Rene Cannao	1dc5eb6581	fix: Fix RAG implementation compilation issues - Use public GenAI_Thread embed_documents() method instead of private LLM_Bridge get_text_embedding() - Fix signedness comparison warning in validate_query_length() - Fix JSON ternary operator type mismatch - Remove unused variables to eliminate warnings - Add GloGATH extern declaration	3 months ago
Rene Cannao	3daaa5c592	feat: Implement RAG (Retrieval-Augmented Generation) subsystem Adds a complete RAG subsystem to ProxySQL with: - RAG_Tool_Handler implementing all MCP tools for retrieval operations - Database schema with FTS and vector support - FTS, vector, and hybrid search capabilities - Fetch and refetch tools for document/chunk retrieval - Admin tools for monitoring - Configuration variables for RAG parameters - Comprehensive documentation and test scripts Implements v0 deliverables from RAG blueprint: - SQLite schema initialization - Source registry management - MCP tools: search_fts, search_vector, search_hybrid, get_chunks, get_docs, fetch_from_source, admin.stats - Unit/integration tests and examples	3 months ago
Rene Cannao	803115f504	Add RAG capability blueprint documents These documents serve as blueprints for implementing RAG (Retrieval-Augmented Generation) capabilities in ProxySQL: - schema.sql: Database schema for RAG implementation - rag_ingest.cpp: PoC ingester blueprint to be integrated into ProxySQL - architecture-data-model.md: Data model architecture for RAG - architecture-runtime-retrieval.md: Runtime retrieval architecture - mcp-tools.md: MCP tools integration design - sql-examples.md: SQL usage examples for RAG - embeddings-design.md: Embeddings design for vector search These files will guide the upcoming RAG implementation in ProxySQL.	3 months ago
René Cannaò	994bafa31f	Merge pull request #17 from ProxySQL/v3.1-MCP2_doc docs: Update MCP documentation to reflect current implementation	3 months ago
Rahim Kanji	5b8bb1952e	Merge remote-tracking branch 'wqv3.1-vec' into v3.1_mcp-http-ssl-toggle	3 months ago
Rene Cannao	aced263367	docs: Update MCP documentation to reflect current implementation This commit completes a comprehensive review and update of all MCP-related documentation: - Remove deprecated FastAPI POC files - Update Architecture.md to reflect implemented multi-endpoint architecture - Update VARIABLES.md with new AI endpoint authentication - Update Tool_Discovery_Guide.md with discovery and LLM tools - Update FTS_Implementation_Plan.md to reflect implemented status - Update Vector_Embeddings_Implementation_Plan.md to show planned status - Update Database_Discovery_Agent.md to clarify conceptual design status - Update scripts/mcp/README.md with current multi-handler architecture - Update STDIO_BRIDGE_README.md with complete tool list All documentation now accurately reflects the current ProxySQL MCP implementation with 6 dedicated tool handlers and two-phase discovery.	3 months ago
Rene Cannao	f01fc79584	feat: Add runtime_mcp_query_rules table and fix stats_mcp_query_rules schema - Add ADMIN_SQLITE_TABLE_RUNTIME_MCP_QUERY_RULES schema (17 columns, same as mcp_query_rules) - Fix STATS_SQLITE_TABLE_MCP_QUERY_RULES to only have rule_id and hits columns - Add runtime_mcp_query_rules detection and refresh in ProxySQL_Admin - Implement save_mcp_query_rules_from_runtime(bool _runtime) for both config and runtime tables - Update get_mcp_query_rules() to return 17 columns (no hits) - get_stats_mcp_query_rules() returns 2 columns (rule_id, hits) Mirrors the MySQL query rules pattern: - mcp_query_rules: config table (17 cols) - runtime_mcp_query_rules: runtime state (17 cols) - stats_mcp_query_rules: hit counters (2 cols)	3 months ago
Rahim Kanji	9b66224df1	Fix critical double-free bug, SQL injection vulnerability, and hardcoded path This commit addresses three issues identified by code review: 1. CRITICAL: Fix double-free bug in MCP server restart logic - Remove manual handler deletions in Admin_FlushVariables.cpp - ProxySQL_MCP_Server destructor already properly cleans up all handlers - Previously caused crashes when toggling SSL mode or changing port - Simplified restart: delete server (destructor cleanup) → create new server - Verified with 10+ rapid SSL toggles without crashes 2. HIGH: Fix SQL injection vulnerability in catalog search - Rewrite MySQL_Catalog::search() to use prepared statements - Use parameter binding (proxy_sqlite3_bind_text/bind_int) for user input - Escape single quotes in FTS5 MATCH clause (doesn't support parameters) - Tested against multiple injection attempts (single quote, backslash, comments, UNION SELECT, kind/tags parameter injection) - All 21 catalog tests still pass with new implementation 3. MEDIUM: Fix hardcoded user-specific path in config - Revert datadir from user-specific absolute path to /var/lib/proxysql - Ensures portability across different environments Testing: - SSL toggle: 7 tests passed (HTTP↔HTTPS, port changes, stress test) - SQL injection: 10 tests passed (various injection attempts blocked) - Catalog functionality: 21 tests passed (FTS5, BM25 ranking, etc.) - Total: 38 tests passed, 0 failed Fixes issues identified in GitHub PR #16 review.	3 months ago
Rahim Kanji	f7397f633c	Fix catalog search to use FTS5 and enhance test suite The catalog_fts FTS5 virtual table was being created but the search() function was using slow LIKE queries instead of FTS5 MATCH operator. Changes to lib/MySQL_Catalog.cpp: - Use FTS5 MATCH with INNER JOIN to catalog_fts when query provided - Add BM25 relevance ranking (ORDER BY bm25(f) ASC) - Significant performance improvement: O(log n) vs O(n) Changes to scripts/mcp/test_catalog.sh: - Add 8 new FTS5-specific tests (CAT013-CAT020): - Multi-term search (AND logic) - Phrase search with quotes - Boolean operators (OR, NOT) - Prefix search with wildcards - Kind and tags filter combinations - Relevance ranking verification - Add SSL/HTTP support with auto-detection - New options: --ssl, --no-ssl, MCP_USE_SSL env var - Fix endpoint path: /query -> /mcp/querywq	3 months ago
Rene Cannao	f9c5a00f8a	chore: Delete temporary discovery output files Remove temporary discovery output files that were previously generated but are now managed elsewhere.	3 months ago
Rene Cannao	f449c4236f	fix: Improve question learning fallback and error logging Two bug fixes for the question learning feature: 1. Fallback to most recent agent_run across all schemas - get_last_agent_run_id() now falls back to the most recent agent_run_id across ALL runs if none exists for the specific run_id - This allows adding questions even when the current schema's discovery didn't include an agent run - Adds logging to show when fallback is used 2. Fix error message extraction for query_tool_calls logging - Fixed bug where error messages weren't being extracted correctly - The old code checked for result["error"]["message"] but create_error_response only has result["error"] (no nested "message" field) - Now correctly extracts result["error"] as a string when present - This ensures failed tool calls are properly logged with error messages This fixes the issue where llm.question_template_add would fail with "No agent run found" even when agent runs exist for other schemas.	3 months ago
Rene Cannao	5b502c0864	feat: Add question learning capability to demo agent Add ability for the demo agent to learn new questions and add them to the catalog, making it smarter over time. Changes: - Added get_last_agent_run_id() function to Discovery_Schema: - Queries agent_runs table for the most recent agent_run_id for a run_id - Returns 0 if no agent runs exist for the schema - Updated llm.question_template_add handler: - Made agent_run_id optional (defaults to 0 when not provided) - When agent_run_id <= 0, auto-fetches last agent_run_id for the schema - Returns helpful error if no agent run exists for the schema - Returns agent_run_id in response for visibility - Updated llm.question_template_add tool schema: - Moved agent_run_id from required to optional parameters - Updated description to explain auto-fetch behavior - Updated demo_agent_claude.sh prompt: - Added llm.question_template_add to available tools - Added Step 4: "Learn from Success" to workflow - Added explicit instruction to ALWAYS LEARN new questions - Added example showing learning workflow - Expanded from 4 steps to 5 steps to include learning Now the demo agent can: 1. Search for existing questions 2. Reuse SQL if a good match exists 3. Generate new SQL if no good match 4. LEARN new questions by adding them to the catalog 5. Present results This enables continuous learning - the more users interact with it, the smarter it becomes.	3 months ago
Rene Cannao	d228142dea	chore: Remove temporary discovery output files and add tmp/ to gitignore Remove temporary files generated during two-phase discovery: - global_database_summary.md (17KB discovery report) - question_templates.md (38KB question templates) Add scripts/mcp/DiscoveryAgent/ClaudeCode_Headless/tmp/ to .gitignore to prevent tracking of temporary discovery outputs in the future.	3 months ago
Rene Cannao	ee74384c79	fix: Prevent llm.search from returning huge object lists in list mode When llm.search is called with an empty query (list mode) to retrieve all available questions, include_objects=true was returning full object schemas for all related objects, resulting in massive responses that could fill the LLM's context and cause rejections. Fix: include_objects now only works when query is non-empty (search mode). When query is empty (list mode), only question templates are returned without object details, regardless of include_objects setting. This makes semantic sense: - Empty query = "list all questions" → just titles/bodies (compact) - Non-empty query = "search for specific questions" → full details including object schemas (for answering the question) Changes: - Modified fts_search_llm() to check !query.empty() before fetching objects - Updated tool schema description to clarify this behavior	3 months ago
Rene Cannao	ba6cfdc8bd	feat: Update demo agent prompt to always pass schema parameter Update the demo_agent_claude.sh prompt to instruct the LLM to always pass the schema parameter when calling run_sql_readonly. Changes: - System prompt now uses unquoted heredoc (ENDPROMPT) to expand $SCHEMA variable - Updated tool description to show schema parameter as required - Updated workflow steps to show schema="$SCHEMA" in llm_search and run_sql_readonly calls - Added explicit instruction: "ALWAYS provide schema="$SCHEMA" to run_sql_readonly" - Updated example interaction to show schema parameter being passed - Changed "Ready to help" line from hardcoded "Chinook" to dynamic $SCHEMA This ensures queries run against the correct database schema, fixing the issue where queries would execute against the default schema instead of the discovered schema.	3 months ago
Rene Cannao	7e522aa2c0	feat: Add schema parameter to run_sql_readonly with per-connection tracking Add optional schema parameter to run_sql_readonly tool that allows queries to be executed against a specific schema, independent of the default schema configured in mcp-mysql_schema. Changes: - Added current_schema field to MySQLConnection structure to track the currently selected schema for each connection in the pool - Added find_connection() helper to find connection wrapper by mysql pointer - Added execute_query_with_schema() function that: - Uses mysql_select_db() instead of 'USE schema' SQL statement - Only calls mysql_select_db() if the requested schema differs from the current schema (optimization to avoid unnecessary switches) - Updates current_schema after successful schema switch - Updated run_sql_readonly handler: - Extracts optional 'schema' parameter - Calls execute_query_with_schema() instead of execute_query() - Returns error response when query fails (instead of success) - Updated tool schema to document the new 'schema' parameter This fixes the issue where queries would run against the default schema (configured in mcp-mysql_schema) instead of the schema being queried, causing "Table doesn't exist" errors when the default schema differs from the discovered schema.	3 months ago
Rene Cannao	a0e72aed03	feat: Add related_objects support to two-phase discovery Update two-phase discovery prompts and script to populate related_objects when creating question templates. Changes: - Updated two_phase_discovery_prompt.md: - Added related_objects parameter to llm.question_template_add tool description - Added instruction to extract table/view names from example_sql - Added example showing proper related_objects format - Updated two_phase_user_prompt.md: - Added example showing how to extract and pass related_objects - Updated two_phase_discovery.py: - Made --schema parameter required (not optional) - Updated usage examples to show required --schema flag - Removed empty string fallback for schema_filter This ensures that question templates created during discovery include the related_objects field, enabling efficient object schema retrieval when templates are searched via llm.search with include_objects=true.	3 months ago
Rene Cannao	7faf993295	feat: Update demo agent script to leverage include_objects and add --help Update the demo_agent_claude.sh script to use the new include_objects parameter and improve usability. Changes: - Updated system prompt to leverage include_objects=true: - llm_search now returns question templates AND object schemas in one call - Removed catalog_get_object from primary workflow (no longer needed) - Reduced workflow from 5 steps to 4 steps - Added explicit instruction to ALWAYS use include_objects=true - Added --help/-h flag with comprehensive usage information - Made schema name mandatory (removed default "Chinook" fallback) - Script now exits with error if no schema is provided - Updated example interaction to show new streamlined workflow This significantly reduces the number of MCP calls needed to answer questions, as object schemas are now included in the initial llm_search response.	3 months ago
Rene Cannao	ee13e4bf13	feat: Add include_objects parameter to llm_search for complete object retrieval Enhance the llm_search MCP tool to return complete question template data and optionally include full object schemas, reducing the need for additional MCP calls when answering questions. Changes: - Added related_objects column to llm_question_templates table - Updated add_question_template() to accept and store related_objects JSON array - Enhanced fts_search_llm() with include_objects parameter: - LEFT JOIN with llm_question_templates to return example_sql, related_objects, template_json, and confidence - When include_objects=true, fetches full object schemas (columns, indexes) for all related objects in a single batch operation - Added error checking for SQL execution failures - Fixed fts_search_llm() get_object() call to pass schema_name and object_name separately instead of combined object_key - Updated Query_Tool_Handler: - Added is_boolean() handling to json_int() helper to properly convert JSON boolean true/false to int 1/0 - Updated llm.search handler to extract and pass include_objects parameter - Updated llm.question_template_add to extract and pass related_objects - Updated tool schemas to document new parameters This change allows agents to get all necessary schema information in a single llm_search call instead of making multiple catalog_get_object calls, significantly reducing MCP call overhead.	3 months ago
Rene Cannao	73d3431c92	fix: Use heredocs for system prompt to preserve special characters Rewrite demo_agent_claude.sh to use heredocs with quoted delimiters for system and append prompts. This prevents bash from interpreting backticks, emojis, and other special characters as commands. Changes: - Use cat > file << 'ENDPROMPT' syntax for prompts - Write prompts to temp files first - Read from files when calling claude CLI - Removed problematic inline variable assignments	3 months ago
Rene Cannao	1b42cfbd27	feat: Add empty query support to llm_search for listing all artifacts Changes: - fts_search_llm(): Empty query now returns all artifacts (list mode) - Update llm.search tool: query parameter is now optional - Tool description mentions empty query lists all artifacts - Add body field to llm_search results - Update demo script: Add special case for "What questions can I ask?" This enables agents to retrieve all pre-defined question templates when users ask what questions are available, instead of inferring questions from schema.	3 months ago
Rene Cannao	be675d4165	wip: Add interactive MCP query agent demo script using Claude Code Add demo_agent_claude.sh script for demonstrating the MCP query agent workflow with Claude Code interactive sessions. The script: - Configures MCP connection via proxysql_mcp_stdio_bridge.py - Sets up system prompt with agent workflow instructions - Demonstrates step-by-step query answering process Note: Script highlights current implementation gaps that need to be addressed before full functionality.	3 months ago
Rene Cannao	5668c86809	fix: Implement FTS indexing for LLM artifacts and fix reserved keyword issue - Rename llm_search_log column from \"limit\" to \"lmt\" to avoid SQL reserved keyword - Add FTS inserts to all LLM artifact upsert functions: - add_question_template(): index question templates for search - add_llm_note(): index notes for search - upsert_llm_summary(): index object summaries for search - upsert_llm_domain(): index domains for search - upsert_llm_metric(): index metrics for search - Remove content='' from fts_llm table to store content directly - Add <functional> header for std::hash usage This fixes the bug where llm_search always returned empty results because the FTS index was never populated.	3 months ago
Rene Cannao	2250b762a3	feat: Add query_tool_calls table to log MCP tool invocations Add query_tool_calls table to Discovery Schema to track all MCP tool invocations via the /mcp/query/ endpoint. Logs: - tool_name: Name of the tool that was called - schema: Schema name (nullable, empty if not applicable) - run_id: Run ID from discovery (nullable, 0 if not applicable) - start_time: Start monotonic time in microseconds - execution_time: Execution duration in microseconds - error: Error message (null if success) Modified files: - Discovery_Schema.cpp: Added table creation and log_query_tool_call function - Discovery_Schema.h: Added function declaration - Query_Tool_Handler.cpp: Added logging after each tool execution	3 months ago
Rene Cannao	8a395b9b47	style: Add spaces around commas in SQL CREATE TABLE statements Format column definitions in CREATE TABLE IF NOT EXISTS statements to have a space before and after each comma (e.g., " , "). This allows ProxySQL Admin to properly display multi-line table schemas. Modified files: - Discovery_Schema.cpp - MySQL_Catalog.cpp - AI_Features_Manager.cpp	3 months ago
Rene Cannao	7c93280174	fix: Escape SQL reserved keyword 'limit' in llm_search_log table The column name 'limit' conflicts with SQL reserved keyword. Escaped as "\"limit\"" to fix table creation.	3 months ago
Rene Cannao	77643859e3	feat: Add timing columns to stats_mcp_query_tools_counters Extend the stats_mcp_query_tools_counters table with timing statistics (first_seen, last_seen, sum_time, min_time, max_time) following the same pattern as stats_mysql_query_digest. All timing values are in microseconds using monotonic_time(). New schema: - tool VARCHAR - schema VARCHAR - count INT - first_seen INTEGER (microseconds) - last_seen INTEGER (microseconds) - sum_time INTEGER (microseconds - total execution time) - min_time INTEGER (microseconds - minimum execution time) - max_time INTEGER (microseconds - maximum execution time)	3 months ago
Rene Cannao	fb66af7c1b	feat: Expose MCP catalog database in ProxySQL Admin interface The MCP catalog database is now accessible as the 'mcp_catalog' schema from the ProxySQL Admin interface, enabling direct SQL queries against discovered schemas and LLM memories.	3 months ago
Rahim Kanji	7564306e18	Handledwq "notifications/initialized" method	3 months ago
Rahim Kanji	4a858521c9	Fix JSON-RPC ID type Change id parameter from string to json& to support JSON-RPC 2.0 spec (id can be string, number, or null)	3 months ago
Rahim Kanji	a15be695e0	Add GET/OPTIONS handlers for MCP HTTP transport - Add render_GET() returning 405 Method Not Allowed - Add render_OPTIONS()	3 months ago
Rene Cannao	35b0b224ff	refactor: Remove mcp-catalog_path variable and hardcode catalog path Remove the mcp-catalog_path configuration variable and hardcode the catalog database path to datadir/mcp_catalog.db for stability. Rationale: The catalog database is session state, not user configuration. Runtime swapping of the catalog could cause tables to be missed and the catalog to fail even if it was succeeding a second earlier. Changes: - Removed catalog_path from mcp_thread_variables_names array - Removed mcp_catalog_path from MCP_Thread variables struct - Removed getter/setter logic for catalog_path - Hardcoded catalog path to GloVars.datadir/mcp_catalog.db in: - ProxySQL_MCP_Server.cpp (Query_Tool_Handler initialization) - Admin_FlushVariables.cpp (MySQL_Tool_Handler reinitialization) - Updated VARIABLES.md to document the hardcoded path - Updated configure_mcp.sh to remove catalog_path configuration - Updated MCP README to remove catalog_path references	3 months ago
Rene Cannao	a816a756d4	feat: Add MCP query tool usage counters to stats schema Add stats_mcp_query_tools_counters and stats_mcp_query_tools_counters_reset tables to track MCP query tool usage statistics. - Added get_tool_usage_stats_resultset() method to Query_Tool_Handler - Defined table schemas in ProxySQL_Admin_Tables_Definitions.h - Registered tables in Admin_Bootstrap.cpp - Added pattern matching in ProxySQL_Admin.cpp - Added stats___mcp_query_tools_counters() in ProxySQL_Admin_Stats.cpp - Fixed friend declaration for track_tool_invocation() - Fixed Discovery_Schema.cpp log_llm_search() to use prepare_v2/finalize	3 months ago
Rene Cannao	393967f511	fix: Use row->cnt instead of row->fields_count	3 months ago

1 2 3 4 5 ...

8324 Commits (fec97bbabec9d4bbddcec90fbd55496fde46a43f) All Branches Search

8324 Commits (fec97bbabec9d4bbddcec90fbd55496fde46a43f)

All Branches