gmakstutis/graphiti
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
704 commits 43 branches 175 tags 21 MiB
Commit graph

4 commits

Author SHA1 Message Date
Claude
13af424b35
Add: Implementation plan for graph exploration tools 
Created comprehensive implementation plan for two new MCP tools:
- get_entity_connections: Direct graph traversal for ALL entity relationships
- get_entity_timeline: Chronological episode history for entities

Plan includes:
- General-purpose PKM focus (architecture, projects, coaching, research)
- Enhanced workflow instructions with decision flowcharts
- Complete code implementation details
- Testing scenarios across multiple domains
- 2-3 hour estimated implementation time

Addresses issue of disconnected/duplicate entities by providing LLM
with complete graph visibility before adding new information.
 2025-11-15 09:41:53 +00:00
Lars Varming
341efd8c3d Fix: Critical database parameter bug + index creation error handling 
CRITICAL FIX - Database Parameter (graphiti_core):
- Fixed graphiti_core/driver/neo4j_driver.py execute_query method
- database_ parameter was incorrectly added to params dict instead of kwargs
- Now correctly passed as keyword argument to Neo4j driver
- Impact: All queries now execute in configured database (not default 'neo4j')
- Root cause: Violated Neo4j Python driver API contract

Technical Details:
Previous code (BROKEN):
  params.setdefault('database_', self._database)  # Wrong - in params dict
  result = await self.client.execute_query(cypher_query_, parameters_=params, **kwargs)

Fixed code (CORRECT):
  kwargs.setdefault('database_', self._database)  # Correct - in kwargs
  result = await self.client.execute_query(cypher_query_, parameters_=params, **kwargs)

FIX - Index Creation Error Handling (MCP server):
- Added graceful handling for Neo4j IF NOT EXISTS bug
- Prevents MCP server crash when indices already exist
- Logs warning instead of failing initialization
- Handles EquivalentSchemaRuleAlreadyExists error gracefully

Files Modified:
- graphiti_core/driver/neo4j_driver.py (3 lines changed)
- mcp_server/src/graphiti_mcp_server.py (12 lines added error handling)
- mcp_server/pyproject.toml (version bump to 1.0.5)

Testing:
- Python syntax validation: PASSED
- Ruff formatting: PASSED
- Ruff linting: PASSED

Closes issues with:
- Data being stored in wrong Neo4j database
- MCP server crashing on startup with EquivalentSchemaRuleAlreadyExists
- NEO4J_DATABASE environment variable being ignored

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-10 11:37:16 +01:00
Lars Varming
8dd7a87623 Improve MCP tool descriptions for better LLM tool selection 
Updated all 12 MCP tool docstrings with:
- LLM-visible priority markers in docstrings (was hidden in meta)
- Decision trees to disambiguate overlapping tools
- Standard Python docstring format with Examples sections
- Enhanced safety protocols for destructive operations
- Increased priority for search_memory_facts (0.85) and get_entities_by_type (0.75)

Changes are docstring-only with no breaking changes to functionality.
Validated with ruff format, ruff check, and py_compile.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 15:05:54 +01:00
Lars Varming
aab233496c Use official Dockerfile.standalone for custom MCP server build 2025-11-08 21:07:28 +01:00