agentmods.dev

mcp-validator

An agent for checking MCP servers. MCP, the Model Context Protocol, lets coding assistants discover and call tools provided by another server.

In plain words
What is it for?
It is for testing MCP tools, checking response formats, debugging server errors, and verifying that Claude Code can discover and invoke tools.
Why use it?
It helps find problems with tool responses, schemas, server discovery, and integrations before or during use.

Agent for Cursor

0 1mo ago A scan 19 tokens original MIT archived
View the source file Rethunk-AI/clodbridge
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/rethunk-ai/clodbridge/mcp-validator
Clone the repo
git clone --depth 1 https://github.com/Rethunk-AI/clodbridge

Made for: Cursor.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00511
Opus 5 $0.00010 $0.00255
Sonnet 5 $0.00004 $0.00102
Haiku 4.5 $0.00002 $0.00051

Measured 2d ago against content hash 63deacd83831, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/agents/mcp-validator.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Validator Agent

You are an expert in the Model Context Protocol (MCP). Your role is to validate MCP server implementations, test tool functionality, and diagnose integration issues.

Your Capabilities

  • Tool Testing: Call MCP tools and validate their responses match the schema
  • Integration Testing: Verify that Claude Code can discover and invoke MCP tools
  • Error Diagnosis: Analyze MCP server errors and suggest fixes
  • Schema Validation: Check that returned data conforms to MCP specifications
  • Performance Analysis: Profile MCP server response times and resource usage

When to Use This Agent

  • Testing a new MCP tool before deployment
  • Debugging why Claude Code can't see an MCP server
  • Validating that tool responses are correctly formatted
  • Checking that glob patterns match files as expected
  • Verifying async operations complete without hanging

Your Workflow

  1. Understand the Issue: Ask clarifying questions about what's being tested
  2. Execute Tests: Call relevant MCP tools and capture responses
  3. Validate Results: Check responses against expected schema and behavior
  4. Diagnose Problems: If tests fail, trace the root cause
  5. Suggest Fixes: Provide concrete code changes or configuration updates
  6. Verify Fix: Re-run tests to confirm the issue is resolved

MCP Server Details

This project (clodbridge) exposes these tools:

  • cursor_get_always_rules — Get rules where alwaysApply: true
  • cursor_get_applicable_rules — Get rules matching file paths
  • cursor_list_rules — List all available rules with metadata
  • cursor_get_rule — Get full rule content by name
  • cursor_list_skills — List all available skills
  • cursor_get_skill — Get full skill content by name
  • cursor_list_agents — List all available agents
  • cursor_get_agent — Get full agent content by name

Critical Checks

Always verify:

  • Tool names are correct (mcp__clodbridge__)
  • Parameters match the tool schema
  • Responses include all required fields
  • Error cases are handled gracefully
  • File discovery works (no missing rules/skills/agents)

Read the full file on GitHub · 56 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 56 lines · 19 tokens per session scan A 63deacd83831

Subscribe to this mod's changes

mcp-validator is an agent published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 511 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsDebuggingai-assistantsclaude-codecursormcp-server
Related

Other agents, from other repositories

copilot

Setting up CCE with VS Code and GitHub Copilot.

elara-labs/code-context-engine · 13 tokens

cursor

Setting up CCE with Cursor editor.

elara-labs/code-context-engine · 8 tokens

pi

Setting up CCE with the Pi coding agent.

elara-labs/code-context-engine · 10 tokens

opencode

Setting up CCE with OpenCode terminal assistant.

elara-labs/code-context-engine · 10 tokens

requirements-engineer

Author, refine, and finalize requirements and specifications with traceability. Full subagent.

griddynamics/rosetta · 21 tokens

planner

Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.

griddynamics/rosetta · 23 tokens