mcp agents

Bbeierle12/Skill-MCP-Claude

Agent Claude Code

Periodic health analyst for the Skill-MCP-Claude repo. Audits the skill catalog, reviews skills individually, checks the MCP server contract, verifies docs accuracy, and proposes new skills. READ-ONLY on code — writes a dated Markdown report only. Use for scheduled (cron) repo health passes or on-demand audits.

tostechbr/memoryClaw

Agent Claude Code

Implements Sprint 0 - Multi-User Isolation for Akashic Context. Use this agent to add userId isolation, per-user workspace/database, working memory (context.json), and memorycontext MCP tool.

henkisdabro/Claude-Code-MCP-Server-Selector

Agent Claude Code

Review code changes focusing on cross-platform compatibility and TypeScript best practices. Use proactively after code changes.

qfoldit/UEFN-TOOLBELT

Agent Claude Code

Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.

KevinRabun/judges

Agent Claude Code

Evaluates code for proper authentication mechanisms, authorization checks, session management, token handling, and access control patterns.

DebugSwift/XcodeBazelMCP

Agent Claude Code

Bazel-first MCP server + CLI for iOS, modeled after getsentry/XcodeBuildMCP but swapping xcodebuild for bazel.

open-mcp-ai/termcp

Agent Claude Code

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

TomMaSS/PRDforge

Agent Claude Code

Use this agent when you need to create or manage Product Requirements Documents using PRDforge. It knows how to use the prd MCP tools to create projects, write sections, set up dependencies, and maintain PRDs as living documents.

mmorris35/devplan-mcp-server

Agent Claude Code

PROACTIVELY use this agent to execute DevPlan MCP Server development subtasks. Expert at DEVELOPMENTPLAN.md execution with cross-checking, git discipline, and verification. Invoke with "execute subtask X.Y.Z" to complete a subtask entirely in one session.

joshsmithxrm/power-platform-developer-suite

Agent Claude Code

You are an adversarial reviewer. You receive an investigation summary and a set of constraints/decisions. Your job is to find blind spots, flawed assumptions, and missing considerations.

archimedes-run/omniHarness

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

buildinternet/releases

Agent Claude Code

Generates an org "overview" knowledge-page body from a composed prompt (the production overview system prompt + release inputs). Used by the key-free sub-agent overview eval (tests/evals/overview-subagent flow) to exercise overview generation on the Claude Code subscription instead of the metered Anthropic API.…

MiaoDX/roboclaws

Agent Claude Code

This file holds repo-specific operating details that are too long for AGENTS.md but useful to coding agents. Read only the sections relevant to the current task.

DikshitRJ/quickfill-mcp

Agent Claude Code

Expert in rendering interactive UIs and dashboards from data.

Xipher-Labs/walter-os

Agent Claude Code

Write external-facing DevRel content — Twitter/X threads, LinkedIn posts, YouTube video scripts, podcast outlines, conference talk abstracts, hackathon submission narratives, customer-facing announcements. Use this subagent when the user asks to "draft a thread", "write a script for the video", "outline the talk"…

ppcvote/claude-tg-windows

Agent Claude Code

Use this agent when you want an adversarial review of a deliverable that the main agent has produced — typically a TG draft, technical document, business analysis, OSS PR description, or strategic recommendation. The critic is adversarial by design: its job is to find what the main agent missed, got wrong, or…

kks3800/Unreal_MCP

Agent Claude Code

Expert in Unreal MCP widget creation. Use for building UIs via MCP commands, Common UI widget priority, and widget blueprint construction patterns.

danielealbano/mcp-for-azure-devops-boards

Agent Claude Code

Expert plan reviewer covering structure, ordering, completeness, QA adequacy, architecture compliance, performance safety, and security across the entire plan. Use when reviewing or writing plans.

k2wanko/voicepeak-mcp

Agent Claude Code

A character role that makes the coding agent speak as Tohoku Itako, a fictional Japanese character with a calm, mysterious personality and specified relationships and speech style.

agatho/trinitycore-mcp

Agent Claude Code

Use this agent when you need performance analysis and optimization guidance for code. Trigger this agent proactively after implementing computationally intensive features, database queries, loops, or algorithms. Examples:\n\n \nContext: User just implemented a creature AI update function that processes all nearby…

chadru/assessor-lookup-public

Agent Claude Code

Entry point for any assessor-lookup task — onboarding a user's local counties, running an MLS discrepancy check, or adding a new county. Plans the work, uses the MCP tools, and delegates site-mapping to the explorer and verification to the reviewer. Start here.

tigu77/tiguclaw

Agent Claude Code

A specialised helper for reviewing code changes, finding bugs, diagnosing causes, and challenging reported problems with counterexamples.

koul777/NCScope

Agent Claude Code

Rapidly classify large NCS interview-question corpora, test failures, and wording defects into actionable quality categories.

kouroshez/coding-os

Agent Claude Code

I value precise decomposition because a problem named wrongly is solved wrongly. I separate problem, behaviour, rules, and risk before anyone writes code, and I name the actors no one else noticed. (constitution values: minimal-context, docs-are-the-contract).