Decision State MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DECISION_STATE_DIR | No | Directory for decision state files. Default is .claude-state relative to working directory. | .claude-state |
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 |
|---|---|
| get_stateB | Return the current project state summary and record counts. |
| update_stateB | Apply a JSON merge patch to state.json and record why the state changed. |
| record_decisionC | Persist a structured decision and update recent_decisions. |
| record_evidenceC | Persist normalized evidence sources, findings, limitations, and confidence. |
| get_task_contextC | Return compact decision-relevant state for a specific task. |
| search_stateC | Search prior decisions and reflections by query text. |
| get_sessionA | Return the active session or a requested session record. |
| reflect_outcomeC | Record the outcome of a previous decision or implementation. |
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 8 tools
Each tool targets a distinct operation or entity: session, state, task context, decision, evidence, outcome, search, and state update. No two tools have overlapping purposes, ensuring clear differentiation for an agent.
Most tools follow a verb_noun pattern with 'get_' for retrieval and 'record_' for persistence, but 'reflect_outcome' deviates from the 'record_' convention. Overall, the naming is predictable and readable.
With 8 tools, the set is well-scoped for a decision state management server. Each tool serves a clear purpose without excess or deficiency.
The tools cover the core lifecycle: reading state, adding decisions/evidence/outcomes, searching, and updating. Minor gaps exist (e.g., no explicit get_decision or update/delete for decisions), but the surface is largely complete for the domain.