personal-kg-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PKG_USE_ANN | No | Use approximate nearest neighbor search | true |
| OPENAI_API_KEY | No | OpenAI API key for semantic embeddings | |
| PKG_STORAGE_DIR | No | Directory for storing knowledge graph data | .kg |
| PKG_GITHUB_TOKEN | No | GitHub Personal Access Token for Personal KG integration | |
| PKG_EMBEDDING_MODEL | No | OpenAI embedding model | text-embedding-3-small |
| PKG_MCP_CAPTURE_AUTO | No | Enable automatic capture without explicit calls | true |
| PKG_MCP_CAPTURE_TOOLS | No | Comma-separated list of MCP tool names to capture | github |
| PKG_AUTO_BACKUP_MINUTES | No | Auto-backup interval in minutes (0 = disabled) | 0 |
| PKG_MCP_CAPTURE_ENABLED | No | Enable automatic capture of MCP tool calls | true |
| PKG_MCP_CAPTURE_EXCLUDE | No | Comma-separated list of MCP tool names to exclude | |
| PKG_GITHUB_INTEGRATION_ENABLED | No | Enable GitHub issue/PR integration | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| kg_captureA | Primary tool for capturing knowledge nodes. Use this to record decisions, progress updates, insights, questions, and ideas. Automatically creates relationships, normalizes tags, and links to sessions. This is your main entry point for adding knowledge to the graph. |
| kg_link_sessionA | Creates a relationship between a session node and another knowledge node. Use to explicitly link work items, decisions, or progress to a specific session for better organization. |
| kg_update_nodeA | Updates an existing knowledge node. Use to modify content, tags, importance, or visibility of a node. Supports partial updates - only specified fields are changed. |
| kg_searchA | Unified search tool for finding knowledge nodes. Supports three modes: 'text' for keyword/tag filtering with ranking, 'semantic' for AI-powered meaning-based search, 'time_range' for date-based queries. Default mode is 'semantic' for best results. |
| kg_query_contextA | Reconstructs context around a specific topic by analyzing related knowledge nodes. Use to understand the full context and background of a particular subject area. |
| kg_list_tagsA | Lists all tags in the knowledge graph with usage counts. Use to discover available tags, find inconsistencies, or identify commonly used categories. |
| kg_get_relevant_contextA | Retrieves relevant past context for a given query. Returns brief summaries of related decisions, insights, and open questions. Perfect for proactive context injection before starting work on a topic. |
| kg_edgesA | Unified tool for relationship operations. Supports: 'create' to link nodes, 'list' to view relationships, 'maintain' for cleanup and rebuilding. |
| kg_adminA | Unified admin tool for maintenance operations. Supports: 'health' for system status, 'backup' for data protection, 'validate' for integrity checks, 'repair' for fixing issues, 'export'/'import' for data migration, 'rename_tag'/'merge_tags' for tag management, 'migrate_embeddings' for backfilling OpenAI embeddings. |
| kg_analyzeA | Unified analysis tool. Supports: 'clusters' for topic grouping, 'emerging' for trend detection, 'graph_export' for full export, 'path' for finding connections between nodes. |
| kg_get_project_stateA | Provides a comprehensive overview of a project's current state including active focus areas, recent decisions, open questions, blockers, and completed tasks. Perfect for project status checks and planning. |
| kg_session_warmupA | Start every session with this tool! Loads comprehensive context about your project including recent work, active questions, and blockers. Essential for maintaining continuity between work sessions. |
| kg_nodeA | Unified tool for node operations. Supports three operations: 'get' to retrieve a node with its relationships, 'delete' to remove a node, 'find_similar' to find semantically similar nodes. |
| kg_capture_sessionA | Captures session summaries with structured metadata. Use at the end of work sessions to record what was accomplished, artifacts created, and next actions. Essential for maintaining context between sessions and tracking progress over time. |
| kg_open_questionsA | Lists unresolved questions with aging information. Questions are considered 'stale' after 3 days. Use to track what needs follow-up and identify forgotten questions. |
| kg_resolve_questionA | Marks a question as resolved by linking it to a decision, insight, or other node that answers it. Creates a 'resolved_by' relationship. |
| kg_diagnosticA | Generate a diagnostic HTML dashboard for debugging knowledge graph context selection, search results, and node visibility. Opens in browser to help understand why certain nodes are included/excluded from context. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
Most tools have clearly distinct purposes, but some overlap exists: kg_search, kg_query_context, and kg_get_relevant_context all retrieve information in different ways, and kg_capture vs kg_capture_session have similar names. The detailed descriptions help disambiguate, but an agent could still misselect between context retrieval tools.
All tools share the 'kg_' prefix, but the naming pattern is mixed: some are verb_noun (kg_list_tags, kg_update_node), some are bare verbs (kg_capture, kg_search), and some are noun-based unified tools (kg_edges, kg_admin, kg_node). This inconsistency makes the set feel less predictable, though the prefix provides a common thread.
With 17 tools, the server is slightly above the ideal range of 3-15, but the count is reasonable for a personal knowledge graph managing nodes, relationships, sessions, questions, and admin operations. The tools collectively cover a broad domain without being excessive.
The tool surface covers the full lifecycle: creation (kg_capture), retrieval (kg_search, kg_node get), update (kg_update_node), deletion (kg_node delete), plus relationship management, session handling, question tracking, project state, admin, and diagnostics. No obvious gaps prevent an agent from performing core knowledge graph operations.