model context protocol hooks

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

Browse within: python 32typescript 15knowledge-management 12agpl 10australia 10open-core 10fastmcp 8desktop-mascot 7electron 7obsidian 7agent-memory 6ai-memory 6dns 6mail 6

PreToolUse

01

cbcoutinho/nextcloud-mcp-server

Hook Claude Code

Runs before the agent uses a tool for Read tool calls, executing pretool-secrets.sh. From cbcoutinho/nextcloud-mcp-server.

340 2d ago A tokens not measured AGPL-3.0

UserPromptSubmit

02

cbcoutinho/nextcloud-mcp-server

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing prompt-secrets.sh. From cbcoutinho/nextcloud-mcp-server.

340 2d ago A tokens not measured AGPL-3.0

PreToolUse

03

vmihalis/hacker-bob

Hook Claude Code

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…

97 3d ago A tokens not measured original Apache-2.0

SubagentStart

04

vmihalis/hacker-bob

Hook Claude Code

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.

97 3d ago A tokens not measured original Apache-2.0

SubagentStop

05

vmihalis/hacker-bob

Hook Claude Code

Runs when a subagent finishes for evaluator-agent, evaluator-fanout, evaluator-evm-agent, evaluator-svm-agent, evaluator-move-agent, evaluator-substrate-agent, evaluator-cosmwasm-agent and evaluator-fanout-child tool calls, executing agent-run-stop.js via node (8 commands). From vmihalis/hacker-bob.

97 3d ago A tokens not measured original Apache-2.0

PreCompact

06

Apra-Labs/apra-fleet

Hook Claude Code

Runs before the context is compacted, running bd prime. From Apra-Labs/apra-fleet.

72 4d ago A tokens not measured

SessionStart

07

Apra-Labs/apra-fleet

Hook Claude Code

Runs when a session starts, running bd prime. From Apra-Labs/apra-fleet.

72 4d ago A tokens not measured

SessionStart

08

cdeust/Cortex

Hook

Runs when a session starts on startup, running an inline shell check. From cdeust/Cortex.

71 3d ago A tokens not measured original MIT

SubagentStart

09

rjkaes/trueline-mcp

Hook

Runs when a subagent starts, executing session-start.js via node. From rjkaes/trueline-mcp.

34 24d ago A tokens not measured copy · 53% Apache-2.0

PreToolUse

10

rjkaes/trueline-mcp

Hook

Runs before the agent uses a tool for Edit, MultiEdit, Read and Bash tool calls, executing pretooluse.js via node. From rjkaes/trueline-mcp.

34 24d ago A tokens not measured original Apache-2.0

PostToolUse

11

rjkaes/trueline-mcp

Hook

Runs after a tool call finishes for mcp__plugin_trueline-mcp_mcp__trueline_edit tool calls, executing posttooluse.js via node. From rjkaes/trueline-mcp.

34 24d ago A tokens not measured original Apache-2.0

UserPromptSubmit

12

youdotcom-oss/dx-toolkit

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, running .claude/hooks/UserPromptSubmit. From youdotcom-oss/dx-toolkit.

25 11d ago A tokens not measured original MIT

PostToolUse

13

vscarpenter/gsd-task-manager

Hook Claude Code

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing lint-on-edit.sh via bash. From vscarpenter/gsd-task-manager.

22 3d ago A tokens not measured original MIT

PreToolUse

14

vscarpenter/gsd-task-manager

Hook Claude Code

Runs before the agent uses a tool for Edit, Write, MultiEdit and Bash tool calls, executing block-sensitive-files.sh and no-main-commits.sh via bash (2 commands). From vscarpenter/gsd-task-manager.

22 3d ago A tokens not measured original MIT

Stop

15

vscarpenter/gsd-task-manager

Hook Claude Code

Runs when the agent finishes a response, running an inline shell check (2 commands). From vscarpenter/gsd-task-manager.

22 3d ago A tokens not measured original MIT

UserPromptSubmit

16

Eigenwise/tesseron

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing inject-docs-index.py via python. From Eigenwise/tesseron.

20 11d ago A tokens not measured

SessionStart

17

husniadil/ultrathink

Hook Claude Code

Runs when a session starts on startup, executing setup_env.sh. From husniadil/ultrathink.

19 4mo ago A tokens not measured original MIT

Stop

18

capazme/mcp-legal-it

Hook

Runs when the agent finishes a response, executing citation-gate.py via python3. From capazme/mcp-legal-it.

14 2d ago A tokens not measured original Apache-2.0

SessionStart

19

AdrianV101/obsidian-pkm-plugin

Hook

Runs when a session starts on startup, clear and compact, executing session-start.js. From AdrianV101/obsidian-pkm-plugin.

13 1mo ago A tokens not measured original MIT

PreToolUse

20

AdrianV101/obsidian-pkm-plugin

Hook

Runs before the agent uses a tool for Bash tool calls, executing pre-commit-reminder.sh. From AdrianV101/obsidian-pkm-plugin.

13 1mo ago A tokens not measured original MIT

SessionStart

21

colliery-io/metis

Hook

Runs when a session starts, executing session-start-hook.sh. From colliery-io/metis.

13 2mo ago A tokens not measured

PreCompact

22

colliery-io/metis

Hook

Runs before the context is compacted, executing pre-compact-hook.sh. From colliery-io/metis.

13 2mo ago A tokens not measured

PostToolUse

23

colliery-io/metis

Hook

Runs after a tool call finishes for Write, Edit and NotebookEdit tool calls, executing post-tool-use-hook.sh. From colliery-io/metis.

13 2mo ago A tokens not measured

PostToolUse

24

Sealjay/mcp-hey

Hook Claude Code

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From Sealjay/mcp-hey.

11 1mo ago A tokens not measured original MIT