MCP tools reference
MCP tools are the low-level primitives your AI uses while it works. You usually do not type them directly; they show up in activity traces as the agent loads memory, checkpoints progress, verifies quality, and closes the session. TRW registers 45 MCP tools for agent use; this page walks through the most common ones, grouped by what they do, so you can tell what the agent is doing and why. Any one session sees a narrower set than that — the server advertises tools per task type by default, which the quick reference below explains.
Quick reference
The most common tools at a glance — the ones you will see most in everyday sessions. The Phase column shows where each tool typically belongs in the six-phase lifecycle.
This page curates a selected set out of the 45 tools the trw-mcp server registers for agent use. Expect your client’s MCP tool listing to show fewer than that, not all of them. By default (tool_resolution_mode: standard) the server advertises only the tools the current task type needs, and a call to a tool outside that set is refused with tool_not_in_surface rather than executed. An agent requests one it needs with trw_request_tool_access; setting tool_resolution_mode: all in .trw/config.yaml turns the narrowing off and advertises every tool at once.
trw_session_startInspect
- Description
- Load prior learnings and recover any active run.
- Phase
- Research
trw_initInspect
- Description
- Create a run directory for progress tracking.
- Phase
- Plan
trw_statusInspect
- Description
- Show current phase, progress, and next steps.
- Phase
- Any
trw_checkpointInspect
- Description
- Save an atomic progress snapshot.
- Phase
- Implement
trw_pre_compact_checkpointInspect
- Description
- Emergency checkpoint before context compaction.
- Phase
- Any
trw_learnInspect
- Description
- Record a discovery for all future sessions.
- Phase
- Review
trw_learn_updateInspect
- Description
- Mark learnings as resolved or obsolete.
- Phase
- Any
trw_recallInspect
- Description
- Search past learnings by keyword, tags, or impact.
- Phase
- Research
trw_instructions_syncInspect
- Description
- Refresh the client instruction file (CLAUDE.md / AGENTS.md / etc.) with the latest TRW protocol.
- Phase
- Deliver
trw_build_checkInspect
- Description
- Record the test, static-check, and coverage results you already ran, for delivery gates. Language-agnostic - it reads your project-native commands, it does not run them.
- Phase
- Validate
trw_reviewInspect
- Description
- Independent code review with rubric scoring.
- Phase
- Review
trw_deliverInspect
- Description
- Persist learnings, sync artifacts, close run.
- Phase
- Deliver
trw_prd_createInspect
- Description
- Generate an AARE-F requirements document.
- Phase
- Plan
trw_prd_validateInspect
- Description
- Check requirements quality and completeness.
- Phase
- Plan
trw_submit_feedbackInspect
- Description
- Submit a bug report, install issue, feature request, or feedback to the TRW maintainer via the authenticated submissions endpoint.
- Phase
- Any
| Tool | Description | Phase |
|---|---|---|
trw_session_start | Load prior learnings and recover any active run. | Research |
trw_init | Create a run directory for progress tracking. | Plan |
trw_status | Show current phase, progress, and next steps. | Any |
trw_checkpoint | Save an atomic progress snapshot. | Implement |
trw_pre_compact_checkpoint | Emergency checkpoint before context compaction. | Any |
trw_learn | Record a discovery for all future sessions. | Review |
trw_learn_update | Mark learnings as resolved or obsolete. | Any |
trw_recall | Search past learnings by keyword, tags, or impact. | Research |
trw_instructions_sync | Refresh the client instruction file (CLAUDE.md / AGENTS.md / etc.) with the latest TRW protocol. | Deliver |
trw_build_check | Record the test, static-check, and coverage results you already ran, for delivery gates. Language-agnostic - it reads your project-native commands, it does not run them. | Validate |
trw_review | Independent code review with rubric scoring. | Review |
trw_deliver | Persist learnings, sync artifacts, close run. | Deliver |
trw_prd_create | Generate an AARE-F requirements document. | Plan |
trw_prd_validate | Check requirements quality and completeness. | Plan |
trw_submit_feedback | Submit a bug report, install issue, feature request, or feedback to the TRW maintainer via the authenticated submissions endpoint. | Any |
Session and workflow
These tools manage one work session. trw_session_start explicitly requests prior learnings and active-run state; checkpoints preserve milestones that a later session can recover after interruption or compaction.
trw_session_startInspect
- What it does
- Load prior learnings and recover any active run.
- When to use
- Start of every session
trw_initInspect
- What it does
- Create a run directory for progress tracking.
- When to use
- New tasks beyond quick fixes
trw_statusInspect
- What it does
- Show current phase, progress, and next steps.
- When to use
- Resuming after interruption
trw_checkpointInspect
- What it does
- Save an atomic progress snapshot.
- When to use
- After each milestone
trw_pre_compact_checkpointInspect
- What it does
- Emergency checkpoint before context compaction.
- When to use
- Automatically before context window fills
| Tool | What it does | When to use |
|---|---|---|
trw_session_start | Load prior learnings and recover any active run. | Start of every session |
trw_init | Create a run directory for progress tracking. | New tasks beyond quick fixes |
trw_status | Show current phase, progress, and next steps. | Resuming after interruption |
trw_checkpoint | Save an atomic progress snapshot. | After each milestone |
trw_pre_compact_checkpoint | Emergency checkpoint before context compaction. | Automatically before context window fills |
Learning and knowledge
These tools record, retrieve, and update durable discoveries. Recall is explicit and ranked against the current query; instruction sync refreshes the managed TRW protocol rather than silently promoting arbitrary learning text.
trw_learnInspect
- What it does
- Record a discovery for all future sessions.
- When to use
- On errors, gotchas, or patterns
trw_learn_updateInspect
- What it does
- Mark learnings as resolved or obsolete.
- When to use
- When issues are fixed
trw_recallInspect
- What it does
- Search past learnings by keyword, tags, or impact.
- When to use
- Before starting unfamiliar work
trw_instructions_syncInspect
- What it does
- Refresh the client instruction file (CLAUDE.md / AGENTS.md / etc.) with the latest TRW protocol.
- When to use
- During delivery or after major discoveries
| Tool | What it does | When to use |
|---|---|---|
trw_learn | Record a discovery for all future sessions. | On errors, gotchas, or patterns |
trw_learn_update | Mark learnings as resolved or obsolete. | When issues are fixed |
trw_recall | Search past learnings by keyword, tags, or impact. | Before starting unfamiliar work |
trw_instructions_sync | Refresh the client instruction file (CLAUDE.md / AGENTS.md / etc.) with the latest TRW protocol. | During delivery or after major discoveries |
Quality and verification
Quality tools record validation outcomes, produce structured review artifacts, and enforce the delivery receipt boundary. Run the real project commands first; these tools preserve and evaluate the evidence rather than replacing the test runner.
trw_build_checkInspect
- What it does
- Record the test, static-check, and coverage results you already ran, for delivery gates. Language-agnostic - it reads your project-native commands, it does not run them.
- When to use
- After implementation
trw_reviewInspect
- What it does
- Independent code review with rubric scoring.
- When to use
- Before committing changes
trw_deliverInspect
- What it does
- Persist learnings, sync artifacts, close run.
- When to use
- End of every task
| Tool | What it does | When to use |
|---|---|---|
trw_build_check | Record the test, static-check, and coverage results you already ran, for delivery gates. Language-agnostic - it reads your project-native commands, it does not run them. | After implementation |
trw_review | Independent code review with rubric scoring. | Before committing changes |
trw_deliver | Persist learnings, sync artifacts, close run. | End of every task |
Requirements
Requirements are the bridge between what you want and what your agent builds. These tools create AARE-F compliant PRDs with EARS-format requirements, then validate them for completeness before implementation begins.
trw_prd_createInspect
- What it does
- Generate an AARE-F requirements document.
- When to use
- Defining new features
trw_prd_validateInspect
- What it does
- Check requirements quality and completeness.
- When to use
- Before implementation begins
| Tool | What it does | When to use |
|---|---|---|
trw_prd_create | Generate an AARE-F requirements document. | Defining new features |
trw_prd_validate | Check requirements quality and completeness. | Before implementation begins |
Feedback
Send the TRW maintainer a bug report, install issue, feature request, or general feedback without leaving your editor. Submissions go through the authenticated platform endpoint, and PII - license keys, API key prefixes, your home path, and sensitive env vars - is redacted client-side before anything leaves your machine.
trw_submit_feedbackInspect
- What it does
- Submit a bug report, install issue, feature request, or feedback to the TRW maintainer via the authenticated submissions endpoint.
- When to use
- When you hit a bug or want to send feedback
| Tool | What it does | When to use |
|---|---|---|
trw_submit_feedback | Submit a bug report, install issue, feature request, or feedback to the TRW maintainer via the authenticated submissions endpoint. | When you hit a bug or want to send feedback |
Usage examples
A connected agent calls these tools when the workflow requires them. These examples show the activity shape you may see as a task moves from startup to delivery.
Common patterns
Tools combine differently depending on task risk and client capability. Start with the smallest pattern that preserves the evidence and handoff the task actually needs.
MCP resources
In addition to tools, TRW exposes 6 read-only MCP resources. Your AI reads these for configuration, state, and templates without making a tool call. Unlike tools, resources are not filtered by task type — all of them are readable in every session.
- Resource
trw://framework/config- What it provides
- Current TRW configuration - ceremony mode, trust level, target platforms
- Resource
trw://framework/versions- What it provides
- Framework and package versions for compatibility checks
- Resource
trw://run/state- What it provides
- Active run phase, checkpoints, and progress metrics
- Resource
trw://learnings/summary- What it provides
- Recent high-impact learnings for the current project
- Resource
trw://templates/prd- What it provides
- PRD requirements-document template (AARE-F)
- Resource
trw://templates/shard-card- What it provides
- Shard-card scaffold for decomposing larger requirements
| Resource | What it provides |
|---|---|
trw://framework/config | Current TRW configuration - ceremony mode, trust level, target platforms |
trw://framework/versions | Framework and package versions for compatibility checks |
trw://run/state | Active run phase, checkpoints, and progress metrics |
trw://learnings/summary | Recent high-impact learnings for the current project |
trw://templates/prd | PRD requirements-document template (AARE-F) |
trw://templates/shard-card | Shard-card scaffold for decomposing larger requirements |
Claude Code MCP tool search
TRW ships 45 MCP tools. Claude Code can defer MCP schemas until they are needed, reducing host-context overhead without changing the server catalog. Other clients own their discovery and schema-loading behavior.
- Behavior
- Template default
- Details
- The bundled Claude Code settings set ENABLE_TOOL_SEARCH=true
- Behavior
- Mechanism
- Details
- Tool schemas are deferred and fetched on demand, reducing prompt overhead for tools not used in the current session
- Behavior
- Opt out
- Details
- Set
ENABLE_TOOL_SEARCH=falsein theenvsection ofa client config file such as .claude/settings.json
- Behavior
- Boundary
- Details
- This changes how Claude Code loads MCP schemas; it does not remove tools from the trw-mcp server
| Behavior | Details |
|---|---|
| Template default | The bundled Claude Code settings set ENABLE_TOOL_SEARCH=true |
| Mechanism | Tool schemas are deferred and fetched on demand, reducing prompt overhead for tools not used in the current session |
| Opt out | Set ENABLE_TOOL_SEARCH=false in the env section of a client config file such as .claude/settings.json |
| Boundary | This changes how Claude Code loads MCP schemas; it does not remove tools from the trw-mcp server |
{
"env": {
"ENABLE_TOOL_SEARCH": "false" // disable deferred schemas
}
}Next steps
Tools are the primitives. Skills show the packaged workflows built on top of them, agents show who uses them, and lifecycle explains when each one should appear.