Skip to content
Agentmart
Submit a tool

Rigour

Lets coding agents review their change, find an existing helper, and recall the team's lessons.

Connector by rigour-labs · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 29
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/rigour-labs-rigour

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Lets coding agents review their change, find an existing helper, and recall the team's lessons.

Use cases: code-review, agent-memory

Reviews

Write a review

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
25 read · 12 write · 2 delete
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Tools by what they do 39

Read from the source code; the running server may list different tools.

Read 25 · Look things up without changing anything.

  • grep
  • list_dir
  • read_file
  • rigour_brief
  • rigour_cache_stats
  • rigour_check
  • rigour_check_deep
  • rigour_check_pattern
  • rigour_context_explain
  • rigour_context_scope
  • rigour_context_stats
  • rigour_deep_stats
Show 13 more tools
  • rigour_explain
  • rigour_get_config
  • rigour_get_fix_packet
  • rigour_hooks_check
  • rigour_list_gates
  • rigour_mcp_get_settings
  • rigour_recall
  • rigour_review
  • rigour_reviewer_verdict
  • rigour_security_audit
  • rigour_status
  • rigour_task_cost
  • search

Write 12 · Create, change, send or run things.

  • git
  • rigour_agent_register
  • rigour_checkpoint
  • rigour_handoff
  • rigour_handoff_accept
  • rigour_hooks_init
  • rigour_index
  • rigour_mcp_set_settings
  • rigour_remember
  • rigour_review_ack
  • rigour_run
  • rigour_run_supervised

Delete 2 · Delete, drop, revoke or wipe things.

  • rigour_agent_deregister
  • rigour_forget

Network hosts it talks to 21

  • api.cursor.com · found in code
  • api.deepseek.com · found in code
  • api.fireworks.ai · found in code
  • api.github.com · found in code
  • api.groq.com · found in code
  • api.mistral.ai · found in code
  • api.mixpanel.com · found in code
  • api.openai.com · found in code
  • api.perplexity.ai · found in code
  • api.together.xyz · found in code
  • claude.com · found in code
  • generativelanguage.googleapis.com · found in code
  • github.com · found in code
  • huggingface.co · found in code
  • momentjs.com · found in code
  • openrouter.ai · found in code
  • react.dev · found in code
  • redux.js.org · found in code
  • rigour.run · found in code
  • rigovo.com · found in code
  • zenodo.org · found in code

Files it touches

  • /dev/null
  • /opt/homebrew/bin
  • /opt/homebrew/bin/rigour
  • /opt/rigour
  • Your home directory (~)
  • Any path the agent passes to its tools

Tools (39)

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

  • git

    Run a read-only git command in the repository: log, show, diff, blame, grep, ls-files, rev-parse, merge-base.

  • grep

    Search tracked files with an extended regular expression. Returns path:line:text matches.

  • list_dir

    List a directory in the repository or the review inputs.

  • read_file

    Read lines of a repository file, numbered. Use it to check callers, callees, types and constants before claiming a defect.

  • rigour_agent_deregisterDeregister Agentcan change or delete data

    Deregister an agent from the multi-agent session. Use when an agent completes its work or needs to release its scope for another agent.

  • rigour_agent_registerRegister Agent

    Register an agent in a multi-agent session. Use this at the START of agent execution to claim task scope and enable cross-agent conflict detection. Required for Agent Team Governance.

  • rigour_briefBrief Before Writingread-only

    Before writing: with goal, the team's rules, lessons and settled points for the task (max 10, cited); with only files, its word on each file you will edit. A [must] you break blocks at review.

  • rigour_cache_statsCache Efficiency Statsread-only

    Returns detailed performance stats across all 4 cache layers (exact hits, semantic hits, partial hits, misses, hit rate, tokens served from cache).

  • rigour_checkRun Quality Gatesread-only

    Run quality gate checks on the project. MUST be called before declaring any coding task complete. By default it judges your change as the stop hook and push gate will: FAIL means something in it must be fixed. **Always show the user the headline summary from this tool's output** — it tells them what Rigour caught. If FAIL, call rigour_get_fix_packet for what to fix, with exact file:line.

  • rigour_check_deepDeep Analysisread-only

    Run quality gates WITH deep LLM-powered analysis. Three-step pipeline: AST extracts facts → LLM interprets → AST verifies. Local-first by default (Qwen2.5-Coder-0.5B lite sidecar), or bring your own API key for any cloud provider.

  • rigour_check_patternCheck Pattern Existsread-only

    CALL THIS BEFORE creating any new function, component, hook, or class. Checks if it already exists in the codebase (prevents duplication), checks for known security vulnerabilities, and BLOCKS writes to protected paths (.github/, CI/CD configs, rigour.yml). Always pass the target file path.

  • rigour_checkpointRecord Checkpoint

    Record a quality checkpoint during long-running agent execution. Use periodically (every 15-30 min) to enable drift detection, quality monitoring, and compact subagent handoffs. Triggers incremental pattern index refresh when filesChanged is provided. Essential for GPT-5.3 coworking mode — call BEFORE rigour_handoff to compress context under 2K tokens.

  • rigour_context_explainContext Explainability Auditread-only

    Audits why specific files/services were included or excluded, cache hit/miss status, invalidation reasons, and prior agent requests.

  • rigour_context_scopeScoped Context Retrievalread-only

    CALL THIS BEFORE reading source files. Returns a minimal editScope (3-10 files) with signatures from the pattern index instead of full file bodies. Uses semantic search when embeddings are available. If index is missing, instructs to call rigour_index first. Highest-impact token saver in the Rigour protocol.

  • rigour_context_statsContext Statsread-only

    Returns context retrieval efficiency, candidate tokens vs returned tokens, potential avoided tokens, cache hit rate, and repeated reads prevented.

Show 24 more tools
  • rigour_deep_statsDeep Analysis Statsread-only

    Get deep analysis statistics from SQLite storage. Returns recent scan scores, top issues, and score trends for a repository.

  • rigour_explainExplain Gate Failuresread-only

    Explain WHY quality gates failed in human-readable language. Use this to understand the reasoning behind each violation before fixing. For machine-readable fix instructions, use rigour_get_fix_packet instead.

  • rigour_forgetDelete Memorycan change or delete data

    Remove a stored memory by key.

  • rigour_get_configGet Configurationread-only

    Returns the current Rigour configuration (rigour.yml) for agent reasoning.

  • rigour_get_fix_packetGet Fix Packetread-only

    After rigour_check FAILs: your change's must-fix items (they block you), then optional notes, paged, each with file:line and the fix. Stay in your change unless a must-fix item names a file. Page with next_offset; re-run rigour_check.

  • rigour_handoffHandoff Task

    Handoff task to another agent in a multi-agent workflow. Use when delegating a subtask or completing your scope. Enables verified handoff governance.

  • rigour_handoff_acceptAccept Handoff

    Accept a pending handoff from another agent. Use to formally acknowledge receipt of a task and verify you are the intended recipient.

  • rigour_hooks_checkFast Hook Check + DLPread-only

    Run the fast hook checker on specific files. Same checks that run inside IDE hooks (Claude, Cursor, Cline, Windsurf). Catches: hardcoded secrets, hallucinated imports, command injection, file size. Completes in <100ms. NEW: Pass 'text' param for DLP mode — scans user input for credentials (AWS keys, API tokens, database URLs, private keys, JWTs) before agent processing.

  • rigour_hooks_initInstall IDE Hooks + DLP

    Generate hook configs for AI coding tools (Claude, Cursor, Cline, Windsurf). Installs real-time quality checks and non-blocking DLP credential warnings by default. Pass dlp=false to disable DLP hooks only.

  • rigour_indexBuild Pattern Index

    Build or update the Rigour pattern index (.rigour/patterns.json). CALL THIS when the index is missing or stale — before rigour_context_scope or rigour_check_pattern. One AST pass extracts functions, classes, routes, and signatures for reuse, embedded locally so rigour_check_pattern can match by intent; semantic=false skips the embeddings.

  • rigour_list_gatesList Quality Gatesread-only

    Lists all configured quality gates and their thresholds for the current project.

  • rigour_mcp_get_settingsGet MCP Settingsread-only

    Get Rigour MCP runtime settings for this repository (.rigour/mcp-settings.json).

  • rigour_mcp_set_settingsSet MCP Settings

    Set Rigour MCP runtime settings for this repository. Currently supports deep_default_mode: off | quick | full.

  • rigour_recallRecall Memoryread-only

    Load stored conventions. At the START of a task, call it with 'query' describing the task to get the few memories that match by meaning, plus promoted team knowledge when team mode is on. With 'key' it returns that memory; with neither, every repository and user memory.

  • rigour_rememberStore Memory

    Store an instruction or convention to remember across sessions. Provide 'key' (short snake_case) and 'value' (the full text). scope: 'repo' (default, this repository), 'user' (all your repositories), or 'team' (this repository, and shared as a team candidate that teammates' agents receive once a person promotes it). Values containing credentials are refused.

  • rigour_reviewReview Changeread-only

    Review the change you just made before calling it done: runs Rigour's gates and keeps only findings on changed lines, each with file, line and a suggested fix. With no diff it reads your uncommitted work from git (new files included); pass base to review the whole branch (e.g. 'main'). Same verdict as `rigour review` in CI.

  • rigour_review_ackAcknowledge Review

    Record that you reviewed a function from rigour_review's review_task: verdict "fixed" (you fixed a defect) or "no_issue", with a note saying what you checked. Covers the function's current code only; editing it later puts it back in the task.

  • rigour_reviewer_verdictReviewer Verdictread-only

    What the model reviewer last decided for this branch: the confirmed items to fix (with id, file:line, consequence and evidence), the disputed ones that are not work, which mode ran, and whether the verdict is for the current commit. Read-only: never runs a model, never dismisses.

  • rigour_runRun Command

    Execute a command under Rigour supervision. This tool can be INTERCEPTED and ARBITRATED by the Governance Studio.

  • rigour_run_supervisedSupervised Execution

    Run a command under FULL Supervisor Mode. Iteratively executes the command, checks quality gates, and returns fix packets until PASS or max retries reached. Use this for self-healing agent loops.

  • rigour_security_auditSecurity Auditread-only

    Runs a live security audit (CVE check) on the project dependencies.

  • rigour_statusQuality Statusread-only

    Quick PASS/FAIL check with JSON-friendly output for polling current project state.

  • rigour_task_costTask Cost Breakdownread-only

    Rigour's estimate of the context and cost its scoped reads avoided for a task, beside any model usage recorded for it.

  • search

    Search the tracked files for a regular expression (git grep -n), optionally under one path.

Signals

Stars
29
Forks
1
Open issues
2
Contributors
3
Last commit
Oct 19, 2026 (11 days ago)
Last release
Oct 19, 2026 (11 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.rigour-labs/rigour
Version
7.0.14
Auth
No auth
Packages
npm @rigour-labs/mcp
License
MIT
Repository
github.com/rigour-labs/rigour
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Rigour MCP server. Agent Mart. https://agentmart.dev/connectors/rigour-labs-rigour (last updated 2026-10-24)