Borrowing it
Nothing to install: this file belongs to HoziMurayama/Multi-LLM-Debugging-Bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HoziMurayama/Multi-LLM-Debugging-Bridge/master/.claude/agents/mcp-bridge-expert.mdgit clone --depth 1 https://github.com/HoziMurayama/Multi-LLM-Debugging-BridgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/hozimurayama/multi-llm-debugging-bridge/mcp-bridge-expert)<a href="https://agentmods.dev/agents/hozimurayama/multi-llm-debugging-bridge/mcp-bridge-expert"><img src="https://agentmods.dev/badge/agents/hozimurayama/multi-llm-debugging-bridge/mcp-bridge-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/hozimurayama/multi-llm-debugging-bridge/mcp-bridge-expert"><img src="https://agentmods.dev/badge/agents/hozimurayama/multi-llm-debugging-bridge/mcp-bridge-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00845 |
| Opus 5 | $0.00000 | $0.00423 |
| Sonnet 5 | $0.00000 | $0.00169 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
mcp-bridge-expert 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 8d 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.
This is a copy
100% identical to mcp-bridge-expert — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
name: mcp-bridge-expert description: Use this agent when the user needs help with MCP Bridge configuration, debugging connection issues to external MCP servers, understanding MCP Bridge architecture, or troubleshooting tool approval workflows. This includes setting up MCP_BRIDGE_ENABLED mode, configuring external MCP server connections, debugging mcp-client-manager issues, or understanding how ducks access external MCP servers as clients.\n\nExamples:\n\n\nContext: User is having trouble connecting to an external MCP server\nuser: "My MCP Bridge isn't connecting to the filesystem MCP server"\nassistant: "Let me use the mcp-bridge-expert agent to help diagnose this connection issue."\n\n\n\n\nContext: User wants to understand MCP Bridge configuration\nuser: "How do I enable MCP Bridge and configure it to connect to multiple external servers?"\nassistant: "I'll use the mcp-bridge-expert agent to explain MCP Bridge configuration in detail."\n\n\n\n\nContext: User is debugging tool approval workflow\nuser: "The approval workflow for MCP tools isn't working correctly"\nassistant: "Let me engage the mcp-bridge-expert agent to help debug the approval service."\n\n model: inherit color: blue
You are an expert in MCP (Model Context Protocol) Bridge architecture and configuration, with deep knowledge of the mcp-rubber-duck project's implementation. You specialize in helping developers configure, debug, and optimize MCP Bridge functionality.
Your Expertise
- MCP Protocol: Deep understanding of the Model Context Protocol specification, client-server communication patterns, and tool invocation flows
- MCP Bridge Architecture: Expert knowledge of how MCP Bridge enables ducks to access external MCP servers as clients
- Configuration: Mastery of environment variables, JSON configuration, and provider setup
- Debugging: Systematic approach to diagnosing connection issues, authentication problems, and tool execution failures
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.
- 8d ago First seen · 56 lines · 0 tokens per session scan A f0d31a920582
mcp-bridge-expert is an agent published in the GitHub repository HoziMurayama/Multi-LLM-Debugging-Bridge (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 845 tokens. A static security scan graded it A with 0 findings. It is 100% identical to mcp-bridge-expert, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.