MEMGRAPH-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TAVILY_API_KEY | No | API key for Tavily backend to enable external web research when no corpus is provided. | |
| AGENT_SYSTEM_EMBEDDING_MODEL | No | Model for sentence-transformers embedding provider. | sentence-transformers/all-MiniLM-L6-v2 |
| AGENT_SYSTEM_EMBEDDING_PROVIDER | No | Embedding provider: 'auto', 'sentence-transformers', or 'hash'. | auto |
| AGENT_SYSTEM_EMBEDDING_CACHE_DIR | No | Path to cache directory for embeddings. | |
| AGENT_SYSTEM_EMBEDDING_LOCAL_ONLY | No | Set to 'true' to use local-only embeddings, or 'false' otherwise. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_project_memoryA | Search project memory by query string and optional type filters. |
| write_project_memoryC | Write a durable memory entry with provenance to the backing store. |
| list_related_artifactsB | List artifacts related to a run or query. |
| record_decisionC | Record a high-value architectural or implementation decision. |
| record_failure_modeA | Record a reusable failure pattern or bug signature. |
| get_file_contextB | Read file context from the orchestrator workspace. |
| checkpoint_runB | Apply a small state patch and create an explicit checkpoint. |
| plan_goalB | Generate a large-app execution blueprint from a high-level goal and optional JSON spec. |
| create_runA | Create a new orchestrator run from a high-level goal and optional JSON spec. |
| resume_runA | Resume an orchestrator run until completion, pause, or failure. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| research_subagent_brief | Template for a bounded research worker |
| code_implementation_brief | Template for a bounded implementation worker |
| review_rubric | Template for review criteria |
| repair_node_brief | Template for bounded repair work |
| decision_recording_template | Template for decision capture |
| large_app_planning_brief | Template for turning a product request into a large-app execution blueprint |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| project_decisions | Active architectural decisions |
| project_interfaces | Active interface and contract memory |
| project_known_bugs | Known reusable failure modes |
| project_conventions | Active patterns and conventions |
| planner_profiles | Available planner profiles and intended use |
TDQS
Scored across 10 tools
Most tools target distinct actions or resources, but plan_goal and create_run both take a high-level goal and optional JSON spec, making their boundaries unclear. Similarly, search_project_memory and list_related_artifacts both retrieve stored information in overlapping ways. Descriptions help clarify intent, but some pairs could still lead to misselection.
All tools follow a consistent verb_noun snake_case pattern, such as resume_run, write_project_memory, record_decision, and create_run. The naming is uniform and predictable across the entire toolset.
Ten tools is a well-scoped count for an orchestrator and memory management server. Each tool covers a meaningful operation without the set feeling bloated or overly sparse.
The core lifecycle is covered: creating and resuming runs, checkpointing, planning, memory read/write, and recording decisions/failures. Minor gaps exist, such as no explicit run status/query tool or delete operation for memory entries, but agents can generally work within the provided surface.