validate-mcp-tools
Validates MCP tool registrations, return shapes, and contract compliance in mcp_server.py.
Skill by amitpuri
Chalk Labs
Need help deploying validate-mcp-tools?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/amitpuri-validate-mcp-tools
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.
About
Use cases: documents, backend, testing, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/validate-mcp-tools
What's inside
- Skill name
validate-mcp-tools- Description
- Validates MCP tool registrations, return shapes, and contract compliance in mcp_server.py. Use when asked to "verify MCP tools", "check tool registration", "did I break the MCP contract", or "test the MCP server".
- License
- unknown
- Instructions
- 97 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from amitpuri/multiagent-retrieval-gaps
- 0.614score
run-test-harness
amitpuri
Runs the full pytest test suite for google-adk-agents and interprets results.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
validate-safety-gate
amitpuri
Validates the deterministic SafetyGateEngine and fail-closed routing invariants.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
add-domain-pack
amitpuri
Add a new clinical domain pack (ontology/domains/<id>/) with its domain skill and competency questions, without changing shared code or role specs.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
add-hazard-detector
amitpuri
Step-by-step workflow for adding a new deterministic Hazard/Gap Detector to the SafetyGateEngine.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
author-runtime-skill
amitpuri
Author or change a runtime Agent Skill (skills/runtime/<name>/ or a domain skill under skills/domains/) and its role wiring.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
deploy-and-teardown
amitpuri
Deploy the agents to Google Cloud, AWS or Azure and remove everything afterwards so nothing keeps billing.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
run-conformance-suite
amitpuri
Check that ADK (GCP), Strands (AWS) and MAF (Azure) make identical decisions on every competency question, offline or against a deployed endpoint.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
run-ontology-build
amitpuri
Build and verify the knowledge release (integrity rules, skills lock, SHACL, OWL 2 RL, release manifest) after changing the ontology, skills or role specs.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
update-model-catalog
amitpuri
Change which model a cloud or role uses (config/models.yaml), including Claude effort and OpenAI reasoning effort per role.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
validate-a2a-contracts
amitpuri
Validates A2A (Agent-to-Agent) message shapes, enum usage, and payload contracts across all agents.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
validate-agent-routing
amitpuri
Traces and validates the full multi-agent routing pipeline from parse through safety_guard_node.
SkillAFreshness: A★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 11, 2026 (25 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from amitpuri
- 0.614score
run-test-harness
amitpuri
Runs the full pytest test suite for google-adk-agents and interprets results.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
validate-safety-gate
amitpuri
Validates the deterministic SafetyGateEngine and fail-closed routing invariants.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
add-domain-pack
amitpuri
Add a new clinical domain pack (ontology/domains/<id>/) with its domain skill and competency questions, without changing shared code or role specs.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
add-hazard-detector
amitpuri
Step-by-step workflow for adding a new deterministic Hazard/Gap Detector to the SafetyGateEngine.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
author-runtime-skill
amitpuri
Author or change a runtime Agent Skill (skills/runtime/<name>/ or a domain skill under skills/domains/) and its role wiring.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
deploy-and-teardown
amitpuri
Deploy the agents to Google Cloud, AWS or Azure and remove everything afterwards so nothing keeps billing.
SkillAFreshness: A★ 5Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get validate-mcp-tools running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
validate-mcp-tools skill. Agent Mart. https://agentmart.dev/skills/amitpuri-validate-mcp-tools (last updated 2026-10-24)