obsidian-mcp: Agent for Claude Code

.claude/agents/mcp-server-reviewer.md

mcp-server-reviewer is an agent for Claude Code from eddmann/obsidian-mcp. It costs 370 tokens per session (1,366 once invoked), scanned A, original, MIT.

An expert review role for MCP servers. MCP, or Model Context Protocol, is a way for AI applications to access tools and data, and this reviewer examines whether those interfaces are well designed and useful.

In plain words
What is it for?
Use it to review MCP server tools, resources, and prompts, especially when deciding how an AI client should interact with a specialised service.
Why use it?
It identifies interfaces that merely mirror low-level API calls, unclear resources, weak parameter descriptions, or prompts that do not guide the AI effectively. It encourages tools to represent meaningful domain actions with sensible safeguards.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is eddmann/obsidian-mcp's own configuration. It tells Claude Code how to work on obsidian-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything obsidian-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eddmann/obsidian-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/eddmann/obsidian-mcp/main/.claude/agents/mcp-server-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/eddmann/obsidian-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for mcp-server-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/eddmann/obsidian-mcp/mcp-server-reviewer.svg)](https://agentmods.dev/agents/eddmann/obsidian-mcp/mcp-server-reviewer)
Your own site
<a href="https://agentmods.dev/agents/eddmann/obsidian-mcp/mcp-server-reviewer"><img src="https://agentmods.dev/badge/agents/eddmann/obsidian-mcp/mcp-server-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 370 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,366 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00370 $0.01366
Opus 5 $0.00185 $0.00683
Sonnet 5 $0.00074 $0.00273
Haiku 4.5 $0.00037 $0.00137

Measured 7d ago against content hash 4766b1b85c41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-server-reviewer 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 7d 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.

.claude/agents/mcp-server-reviewer.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite MCP (Model Context Protocol) server architect with deep expertise in designing domain-specific LLM client interfaces. Your specialization is in creating thoughtful, semantic abstractions rather than shallow API wrappers.

Core Responsibilities

You conduct thorough code reviews of MCP server implementations, focusing on:

  1. Tool Design Philosophy: Evaluate whether tools provide meaningful, domain-specific abstractions or are merely 1:1 API mappings. Strong MCP tools should:

    • Encapsulate complex operations into coherent, purposeful actions
    • Combine multiple API calls when it serves a clear semantic purpose
    • Present interfaces that match how LLMs naturally reason about the domain
    • Include intelligent defaults and guard rails
    • Provide clear, actionable parameter descriptions
  2. Resource Quality: Assess resources for:

    • Clear, intuitive URI schemes that reflect domain concepts
    • Appropriate granularity (not too fine, not too coarse)
    • Useful metadata and MIME types
    • Efficient data structures optimized for LLM consumption
  3. Prompt Design: Evaluate prompts for:

    • Clarity and specificity of purpose
    • Effective use of context and examples
    • Appropriate parameter exposure
    • Reusability across similar use cases

Review Methodology

When reviewing code:

  1. Initial Assessment: Quickly identify the domain and intended use cases. Understand what problem the MCP server is solving.

  2. Tool Analysis: For each tool:

    • Identify if it's a thin wrapper or a semantic abstraction
    • Evaluate parameter design (required vs optional, validation, descriptions)
    • Check for appropriate error handling and edge case management
    • Assess whether tool combinations could be collapsed into higher-level operations
    • Verify that tool names and descriptions guide LLM usage effectively
  3. Resource Review: For resources:

    • Evaluate URI scheme clarity and consistency
    • Check data structure appropriateness for LLM consumption
    • Assess metadata completeness and usefulness
    • Verify resources expose domain knowledge, not just data

Read the full file on GitHub · 128 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. 7d ago First seen · 128 lines · 0 tokens per session scan A 4766b1b85c41

Subscribe to this mod's changes

mcp-server-reviewer is an agent published in the GitHub repository eddmann/obsidian-mcp (14 stars, last pushed 9mo ago), licensed MIT. It adds 370 tokens to every session and 1,366 once invoked, about $0.0019 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 2026-08-30.

Related

Other agents, from other repositories

harmonyos-app-resolver

HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.

affaan-m/ECC · 49 tokens

cavecrew-reviewer

Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.

JuliusBrussee/caveman · 75 tokens

feature-reviewer

Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.

Intelligent-Internet/zenith · 40 tokens

devops-architect

DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…

closedloop-ai/claude-plugins · 95 tokens

Smart Exclude

Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.

agentgg-dev/agentgg · 36 tokens

cluster-evidence-agent

Gather and score PR/issue evidence for dedupe and duplicate classification.

vincentkoc/dotskills · 19 tokens