AI Architect MCP Spec

Install

Works with Claude Desktop. Read the repository before you give any tool access to your data.

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

14 read · 0 write · 3 delete

Secrets

None asked for

Install scripts

None found

Runs as

Downloaded binary

Tools (17)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• check_healthread-only

  Check system health — verify all components are accessible

• conclude_verificationcan change or delete data

  Aggregate JudgeVerdict[] from spawned subagents into a VerificationReport (consensus + dissent). IMPORTANT: omitting claim_types when a reliability repository is open suppresses observation flushing for this batch — the calibration data will be missing for these runs (one-sided censoring).

• coordinate_context_budgetread-only

  Calculate token budget allocation for PRD generation. Returns per-section retrieval limits for Cortex recall, generation budgets, and section-specific query templates. Call this BEFORE starting section generation.

• get_configread-only

  Get the full skill configuration

• get_pipeline_stateread-only

  Read the current pipeline state by run_id. format:'summary' (default) returns the lightweight envelope; format:'full' returns the whole state, bounded to the Claude Code 100,000-char MCP response budget by shedding least-relevant detail first (observable __bounded markers; full grounding re-fetchable via format:'grounding'); format:'grounding' returns the codebase_grounding (+ prd_validation when it fits) blobs format:'full' sheds first; format:'validation' returns prd_validation alone (the blob format:'grounding' sheds when the pair overshoots); format:'action' returns the UNBOUNDED last acti…

• get_prd_context_inforead-only

  Get configuration for a specific PRD context type

• get_quality_historyread-only

  Get historical PRD quality scores from the evidence repository

• get_strategy_effectivenessread-only

  Get strategy performance data — actual vs expected improvement, compliance rate

• list_available_strategiesread-only

  List thinking strategies available to the pipeline.

• map_failure_to_retrievalread-only

  When validate_prd_section returns violations, call this to get corrective Cortex recall queries. Closes the validation→retrieval feedback loop so retries use better context.

• plan_document_verificationread-only

  Same as plan_section_verification but across all sections of a document.

• plan_section_verificationread-only

  Extract claims from a PRD section and select judges. Returns JudgeRequest[] the host must execute via Agent tool in parallel.

• read_skill_configread-only

  Read the SKILL.md content that drives PRD generation

• start_pipelinecan change or delete data

  Initialize a new PRD pipeline run. Returns run_id and the first NextAction the host must execute.

• submit_action_resultcan change or delete data

  Feed an ActionResult to the pipeline runner; receive the next NextAction.

Signals

Stars

6

Forks

1

Open issues

10

Last commit

Oct 23, 2026 (7 days ago)

Last release

Aug 10, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.cdeust/ai-architect-mcp-spec

Version

0.8.0

Auth

No auth

Packages

mcpb https://github.com/cdeust/ai-architect-mcp-spec/releases/download/v0.8.0/ai-architect-mcp-spec.mcpb

License

MIT

Repository

github.com/cdeust/ai-architect-mcp-spec

Website

ai-architect.tools

First seen

Oct 24, 2026

Last checked

Oct 25, 2026

Source

Official MCP Registrygithub-graphql