610 tagged mcp, measured the same way as everything else here.
Browse within: model-context-protocol 192claude-code-plugin 128agent-memory 90local-first 66Multi-Agent 59ai-coding 57ai-tools 54knowledge-graph 52ai-memory 39knowledge-base 30knowledge-management 30fastmcp 28ai-assistant 25codex-plugin 25
Hook Claude Code
One of 2 in settings.json
Runs before the agent uses a tool for Bash, mcp__github__push_files and mcp__github__create_or_update_file tool calls, executing require-review.sh via bash (3 commands). From Nosmoht/talos-mcp-server.
Hook
One of 4 in hooks.json
Runs when a session starts, running mneme hook session-start. From OnourImpram/mneme.
Hook Claude Code
One of 2 in settings.json
Runs when a session starts, executing klon-aktualitaet.sh. From malkreide/sbb-opendata-mcp.
Hook Claude Code
One of 2 in settings.json
Runs when a session starts, executing session-start.sh. From malkreide/swiss-democracy-mcp.
Hook
Runs when you submit a prompt, before the agent sees it, executing glm_router_hook.mjs via node. From djerok/glm-mcp.
Hook Claude Code
One of 2 in settings.json
Runs when a session starts on startup, resume, clear and compact, running vectr hook session-start. From swapnanil/vectr.
Hook Claude Code
One of 2 in settings.json
Runs when a session starts, executing session-start.sh. From moureauf/boe-mcp.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From Whitening-Sinabro/clouvel.
Hook Claude Code
One of 2 in settings.json
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From shelby-protocol/memory-forge.
Hook Claude Code
One of 2 in settings.json
Runs after a tool call finishes for Write and Edit tool calls, running bun x ultracite fix. From ImBIOS/tool-search-mcp.
jeremylongshore/intent-eval-lab
Hook Claude Code
One of 3 in settings.json
Runs before the context is compacted, running bd prime. From jeremylongshore/intent-eval-lab.
Hook
One of 4 in hooks.json
Runs when you submit a prompt, before the agent sees it, executing prompt-router.cjs via node. From ShipToday/forge-plugin-codex.
Hook
Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, running echo 'Tip: project-specific conventions should be stored as . From Obidel/Agentmemory.
forbiddenlink/mcp-token-tracker
Hook Claude Code
One of 2 in settings.json
Runs after a tool call finishes for mcp__* tool calls, executing mcp-tool-logger.sh. From forbiddenlink/mcp-token-tracker.
Hook Claude Code
One of 2 in settings.json
Runs before the agent uses a tool for Glob and Grep tool calls, running an inline shell check. From mahdisanagostar/chef.
subkoks/BEST-Self-Enhancement-Learning-AI
Hook Claude Code
One of 2 in settings.json
Runs when a session starts on startup and resume, executing cloud-setup.sh via bash. From subkoks/BEST-Self-Enhancement-Learning-AI.
Hook Claude Code
One of 2 in settings.json
Runs before the agent uses a tool for Bash tool calls, executing ssh-bash-nudge.mjs via node. From hunchom/claude-code-ssh.
Hook
One of 3 in hooks.json
Runs after a tool call finishes for edit_file and edit_files tool calls, executing graphmind-post-tool-use.mjs via node. From kostya-pakhomov/graphmind.
olgasafonova/mcp-servercard-go
Hook Claude Code
One of 2 in settings.json
Runs when a session starts, running bd prime --hook-json. From olgasafonova/mcp-servercard-go.
jerfowler/agent-comm-mcp-server
Hook Claude Code
One of 3 in settings.json
Runs when you submit a prompt, before the agent sees it, executing reasoning-validator.py. From jerfowler/agent-comm-mcp-server.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check (2 commands). From getlien/lien.
Hook Claude Code
One of 6 in settings.json
Runs when a session starts, executing index.js via node. From GreXLin85/notnessie.
Hook
Runs before the agent uses a tool for ^apply_patch$ tool calls, executing pre-edit-check.mjs via node. From workspace-json/codex-mcp.
Hook Claude Code
One of 2 in settings.json
Runs before the agent uses a tool for Agent and Workflow tool calls, running an inline shell check. From coo1white/cool-workflow.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: