mcp hooks

610 tagged mcp, measured the same way as everything else here.

Browse within: model-context-protocol 190claude-code-plugin 128agent-memory 85local-first 66Multi-Agent 59ai-coding 53knowledge-graph 51ai-memory 39knowledge-base 30knowledge-management 29fastmcp 28codex-plugin 25markdown 24ai-assistant 23

SessionStart

49

agenticmail/agenticmail

Hook

One of 3 in hooks.json

Runs when a session starts, running agenticmail-codex-mail-hook. From agenticmail/agenticmail.

not rated 212 22d ago A tokens not measured original MIT

UserPromptSubmit

50

agenticmail/agenticmail

Hook

One of 3 in hooks.json

Runs when you submit a prompt, before the agent sees it, running agenticmail-codex-mail-hook. From agenticmail/agenticmail.

not rated 212 22d ago A tokens not measured copy · 89% MIT

Stop

51

agenticmail/agenticmail

Hook

One of 3 in hooks.json

Runs when the agent finishes a response, running agenticmail-codex-mail-hook. From agenticmail/agenticmail.

not rated 212 22d ago A tokens not measured copy · 86% MIT

PostToolUse

52

postrv/narsil-mcp

Hook Claude Code

One of 5 in settings.json

Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing post-edit-scan.sh. From postrv/narsil-mcp.

not rated 181 3mo ago A tokens not measured original Apache-2.0

Stop

53

postrv/narsil-mcp

Hook Claude Code

One of 5 in settings.json

Runs when the agent finishes a response, executing end-of-turn.sh. From postrv/narsil-mcp.

not rated 181 3mo ago A tokens not measured original Apache-2.0

SessionStart

54

postrv/narsil-mcp

Hook Claude Code

One of 5 in settings.json

Runs when a session starts, executing session-init.sh. From postrv/narsil-mcp.

not rated 181 3mo ago A tokens not measured original Apache-2.0

PreToolUse

55

paiml/paiml-mcp-agent-toolkit

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Write and Edit tool calls, executing pmat-quality-feedback.sh. From paiml/paiml-mcp-agent-toolkit.

not rated 164 today A tokens not measured original MIT

PostToolUse

56

dcostenco/prism-coder

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Bash tool calls, executing post-commit-repomix.sh via bash. From dcostenco/prism-coder.

not rated 157 yesterday A tokens not measured original Apache-2.0

Notification

57

codingagentsystem/cas

Hook Claude Code

One of 12 in settings.json

Runs when the agent sends a notification for permission_prompt, idle_prompt and auth_success tool calls, running cas hook Notification. From codingagentsystem/cas.

not rated 160 5mo ago A tokens not measured original MIT

PreToolUse

58

codingagentsystem/cas

Hook Claude Code

One of 12 in settings.json

Runs before the agent uses a tool for Read, Glob, Grep, Write, Edit, Bash, WebFetch, WebSearch, Task and SendMessage tool calls, running cas hook PreToolUse. From codingagentsystem/cas.

not rated 160 5mo ago A tokens not measured original MIT

SessionStart

59

codingagentsystem/cas

Hook Claude Code

One of 12 in settings.json

Runs when a session starts, running cas hook SessionStart (2 commands). From codingagentsystem/cas.

not rated 160 5mo ago A tokens not measured original MIT

PostToolUse

60

bobmatnyc/claude-mpm

Hook Claude Code

One of 9 in settings.json

Runs after a tool call finishes for Write, MultiEdit, Edit and NotebookEdit tool calls, running claude-hook (2 commands). From bobmatnyc/claude-mpm.

not rated 149 3d ago A tokens not measured

PostToolUseFailure

61

bobmatnyc/claude-mpm

Hook Claude Code

One of 9 in settings.json

Runs when a tool call fails, running python3. From bobmatnyc/claude-mpm.

not rated 149 3d ago A tokens not measured

UserPromptSubmit

62

bobmatnyc/claude-mpm

Hook Claude Code

One of 9 in settings.json

Runs when you submit a prompt, before the agent sees it, running claude-hook (2 commands). From bobmatnyc/claude-mpm.

not rated 149 3d ago A tokens not measured

PreToolUse

63

HsienW/chat-gun-react-agent

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Edit, MultiEdit, Write, NotebookEdit, Bash and mcp__.* tool calls, executing ccr-role-write-guard.mjs via node. From HsienW/chat-gun-react-agent.

not rated 135 +1 yesterday A tokens not measured

PostToolUse

64

helixml/kodit

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From helixml/kodit.

not rated 123 +1 1mo ago A tokens not measured original Apache-2.0

PostToolUse

65

aikts/yandex-tracker-mcp

Hook Claude Code

One of 7 in settings.json

Runs after a tool call finishes for Task and TodoWrite tool calls, running an inline shell check (2 commands). From aikts/yandex-tracker-mcp.

not rated 113 2d ago A tokens not measured copy · 86% Apache-2.0

PreToolUse

66

aikts/yandex-tracker-mcp

Hook Claude Code

One of 7 in settings.json

Runs before the agent uses a tool for Task tool calls, running an inline shell check. From aikts/yandex-tracker-mcp.

not rated 113 2d ago A tokens not measured copy · 81% Apache-2.0

SessionStart

67

aikts/yandex-tracker-mcp

Hook Claude Code

One of 7 in settings.json

Runs when a session starts, running an inline shell check. From aikts/yandex-tracker-mcp.

not rated 113 2d ago A tokens not measured original Apache-2.0

PreToolUse

68

jayminwest/kotadb

Hook Claude Code

One of 5 in settings.json

Runs before the agent uses a tool for Edit, Write, MultiEdit, Edit and Write tool calls, executing pre-edit-context.py and scope-enforcement.ts via python3 (2 commands). From jayminwest/kotadb.

not rated 102 4mo ago A tokens not measured original MIT

SubagentStart

69

jayminwest/kotadb

Hook Claude Code

One of 5 in settings.json

Runs when a subagent starts for build and Explore tool calls, executing agent-context.py via python3. From jayminwest/kotadb.

not rated 102 4mo ago A tokens not measured original MIT

SessionStart

70

jayminwest/kotadb

Hook Claude Code

One of 5 in settings.json

Runs when a session starts, executing session-expertise.py via python3. From jayminwest/kotadb.

not rated 102 4mo ago A tokens not measured original MIT

PreToolUse

71

vmihalis/hacker-bob

Hook Claude Code

One of 5 in settings.json

Runs before the agent uses a tool for Bash, Read, Grep, Write, Edit, MultiEdit, mcp__hacker-bob__bob_http_scan, mcp__hacker-bob__bob_write_wave_handoff, mcp__hacker-bob__bob_finalize_agent_run, Agent and Task tool calls, executing session-write-guard.sh, session-read-guard.sh, bob-http-write-confirm.sh and…

not rated 97 5d ago A tokens not measured original Apache-2.0

SubagentStart

72

vmihalis/hacker-bob

Hook Claude Code

One of 5 in settings.json

Runs when a subagent starts for evaluator-agent, evaluator-fanout, evaluator-evm-agent, evaluator-svm-agent, evaluator-move-agent, evaluator-substrate-agent and evaluator-cosmwasm-agent tool calls, executing agent-run-start.js via node (7 commands). From vmihalis/hacker-bob.

not rated 97 5d ago A tokens not measured original Apache-2.0

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: