model-context-protocol agents

541 tagged model-context-protocol, measured the same way as everything else here.

Browse within: agent-memory 39knowledge-graph 33enterprise-architecture 30arckit 29governance 29documentation 28CVE 21appsec 21code-search 21codium 21derivative 21fuzzing 21operators 21markdown 19

backlog-groomer

25

Apra-Labs/apra-fleet

Agent

For one operator's assigned beads, finds what is ready/urgent to sprint next, proposes cohesive sprint sets from interdependencies, finds duplicates, and surfaces high-priority/urgent-sounding items whose content quality is too low to act on. Full beads mutation authority (merge/close/defer/reject), always…

72 5d ago A 79 tokens

doer

26

Apra-Labs/apra-fleet

Agent

Works assigned bead ids (task-type work, impl and test-dev), commits after each, stops at VERIFY checkpoint.

72 5d ago A 26 tokens

integ-test-runner

27

Apra-Labs/apra-fleet

Agent

Runs integ-test-playbook.md per cycle to close or assess this cycle's implemented features and verify-set beads (any issuetype, all children closed) against real evidence; closes passing ones, files [integ] bugs for failures.

72 5d ago A 53 tokens

Warp-mcp

28

Aqualia/Alph

Agent

Warp Terminal MCP – Integration with Alph Overview: Warp is a modern terminal that features an “Agent Mode” with AI assistance. Warp supports MCP servers as modular plugins to extend its AI agents with custom tools and data[18]. Integrating Alph with Warp means configuring Warp’s MCP client to know about Alph’s MCP…

69 7mo ago A 0 tokens original MIT

Windsurf-mcp

29

Aqualia/Alph

Agent

Windsurf Cascade MCP – Integration with Alph Overview: Windsurf (formerly Codeium’s editor) includes Cascade, an AI agent that can leverage external tools via the Model Context Protocol (MCP)[1]. To integrate Alph with Windsurf, Alph must configure Windsurf’s MCP client to recognize and launch Alph’s MCP server. This…

69 7mo ago A 0 tokens original MIT

protocol-examples

30

Aqualia/Alph

Agent

These examples show how Alph renders MCP server configuration for different agents and transports.

69 7mo ago A 0 tokens original MIT

claude-code

31

metedata/Remarc

Agent

Connect Claude Code to Remarc with the remarc plugin, and optionally let comments wake live sessions with remarc-hooks.

66 11d ago A 24 tokens original MIT

omp

32

metedata/Remarc

Agent

Install Remarc's public OMP plugins, verify the MCP connection, and pair a session for instant comment delivery.

66 11d ago A 23 tokens original MIT

webhooks

33

metedata/Remarc

Agent

Send Remarc comment events as HTTP POST JSON to Zapier, Make, n8n, IFTTT, Slack, or any other endpoint that accepts JSON.

66 11d ago A 33 tokens original MIT

issue-tracker

34

rookslog/zlibrary-mcp

Agent

Issues and specs for this repo live as GitHub issues. Use the gh CLI for all operations.

65 9d ago A 0 tokens copy · 98% MIT

assumption-auditor

35

Kastalien-Research/thoughtbox

Agent Claude Code

Proactively audit the assumption registry for stale, unverified, or newly-broken assumptions. Use on a schedule (weekly) or when starting work that depends on external systems. Unlike dependency-verifier (reactive, investigates on demand), this agent walks the full registry and flags what needs attention.

64 1mo ago A 65 tokens original MIT

cost-governor

36

Kastalien-Research/thoughtbox

Agent Claude Code

Track aggregate token spend and API costs across all agent operations. Enforce budget constraints, detect cost anomalies, and recommend budget reallocation. Use for daily cost rollups, budget enforcement, and spend optimization.

64 1mo ago A 46 tokens original MIT

devils-advocate

37

Kastalien-Research/thoughtbox

Agent Claude Code

Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…

64 1mo ago A 66 tokens original MIT

task-checker

38

WYRE-AI/autotask-mcp

Agent Claude Code

Agent "task-checker" from WYRE-AI/autotask-mcp, covering core responsibilities, verification workflow, output format, decision criteria and important guidelines.

49 2d ago A 177 tokens original Apache-2.0

task-executor

39

WYRE-AI/autotask-mcp

Agent Claude Code

name: task-executor description: Use this agent when you need to implement, complete, or work on a specific task that has been identified by the task-orchestrator or when explicitly asked to execute a particular task. This agent focuses on the actual implementation and completion of individual tasks rather than…

49 2d ago A 303 tokens original Apache-2.0

task-orchestrator

40

WYRE-AI/autotask-mcp

Agent Claude Code

Agent "task-orchestrator" from WYRE-AI/autotask-mcp, covering core responsibilities, operational workflow, initial assessment phase, executor deployment phase and coordination phase.

49 2d ago A 352 tokens original Apache-2.0

agent-workflows

41

TAJD/projektor

Agent

How Projektor fits the agentic dev-tools stack, and the end-to-end multi-agent loop: lifecycle, coordination, and project management.

39 8d ago A 28 tokens original MIT

mcp-connection

42

TAJD/projektor

Agent

Connect Claude Code or any MCP-compatible agent to your Projektor instance.

39 8d ago A 14 tokens original MIT

tool-catalog

43

TAJD/projektor

Agent

Every MCP tool Projektor exposes, generated from source.

39 8d ago A 11 tokens original MIT

performance-analyst

44

FerroxLabs/tvcontrol

Agent

Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.

37 5d ago A 32 tokens

architect

45

u9401066/pubmed-search-mcp

Agent

A system architecture design agent that reads the project’s stored notes and applies Domain-Driven Design (DDD), an approach that organizes software around business concepts.

26 15d ago A 44 tokens

orchestrator

46

u9401066/pubmed-search-mcp

Agent

A coordinating agent that breaks complex requests into smaller tasks, assigns them to specialised agents, and tracks progress.

26 15d ago A 58 tokens

research

47

u9401066/pubmed-search-mcp

Agent

Research assistant for PubMed Search MCP plus Zotero Keeper MCP. Uses collaboration-safe search, duplicate-check, and import workflow.

26 15d ago A 25 tokens

feedback-triage

48

korovin-aa97/talkthrough-mcp

Agent

Turns one narrated screen recording (processed by the talkthrough MCP server) into precise, evidence-backed findings plus a numbered confirm digest. Never files issues itself — it produces the findings JSON; filing happens only after the recording author approves.

24 3d ago A 51 tokens original MIT