156 tagged mcp-server, measured the same way as everything else here.
Browse within: model-context-protocol 52claude-code-plugin 40claude-ai 22local-first 22ai-memory 18agent-memory 16ai-coding 16knowledge-graph 15docker 11australia 9automation-engine 9belief-revision 9beta 9end-to-end-testing 9
Hook Claude Code
One of 2 in settings.json
Runs after a tool call finishes for mcp__sk-wwise-* tool calls, executing log_tool.py via python. From silver-rain-dev/sk-wwise-mcp.
Hook Claude Code
One of 4 in settings.json
Runs when a session starts, executing session-start.sh. From fruggr/zendesk-mcp-server.
Hook Claude Code
One of 4 in settings.json
Runs before the agent uses a tool for mcp__github__create_pull_request, mcp__github__update_pull_request, mcp__github__add_issue_comment, mcp__github__add_comment_to_pending_review, mcp__github__add_reply_to_pull_request_comment, mcp__github__pull_request_review_write and mcp__github__issue_write tool calls, running…
Hook Claude Code
One of 4 in settings.json
Runs after a tool call finishes for Edit and Write tool calls, executing biome.mjs with --write, --skip and --no-errors-on-unmatched. From fruggr/zendesk-mcp-server.
Hook Claude Code
One of 3 in settings.json
Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing protect-files.sh and enforce-pr-review.sh (2 commands). From mean-weasel/bullhorn.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Edit and Write tool calls, executing auto-format.sh, typecheck.sh, lint-security.sh and run-related-tests.sh (4 commands). From mean-weasel/bullhorn.
Hook Claude Code
One of 2 in settings.json
Runs when a session starts, running an inline shell check. From AndyForest/SoupNet.
Hook Claude Code
One of 2 in settings.json
Runs when the agent finishes a response, executing stop-verify.sh via bash. From aoreshkov/oracle-forms-mcp.
Hook
One of 3 in hooks.json
Runs on the AfterAgent event, executing hook-runner.cjs via node. From djinn-soul/gemini-mem.
Hook
One of 3 in hooks.json
Runs on the BeforeAgent event, executing hook-runner.cjs via node. From djinn-soul/gemini-mem.
Hook
One of 3 in hooks.json
Runs when a session starts, executing hook-runner.cjs via node. From djinn-soul/gemini-mem.
Hook Claude Code
One of 2 in settings.json
Runs before the agent uses a tool for Edit and Write tool calls, running an inline shell check. From an0malous/mcp-custos.
Hook Claude Code
One of 6 in settings.json
Runs when a session starts, executing session-start-lock.sh, heal-primary-branch.sh, code-search-up.sh and memory-nudge.sh via bash with --for-hook (9 commands). From retospect/precis-mcp.
Hook Claude Code
One of 6 in settings.json
Runs before the agent uses a tool for Edit, Write, MultiEdit, NotebookEdit, Read, Bash, Grep, mcp__precis__put, mcp__precis__edit, mcp__precis__delete and mcp__precis__tag tool calls, executing guard-worktree-path.py, guard-sealed-migration.py, rca-triage-nudge.py, guard-secret-read.py, guard-commit-on-main.py…
Hook Claude Code
One of 6 in settings.json
Runs after a tool call finishes for Write tool calls, executing map-staleness-reminder.py and session-size-nudge.py via python3 (2 commands). From retospect/precis-mcp.
Hook Claude Code
One of 3 in settings.json
Runs before the context is compacted, executing pre_compact.py via python. From spideynolove/memory.
Hook Claude Code
One of 3 in settings.json
Runs when you submit a prompt, before the agent sees it, executing user_prompt_submit.py and context_router.py via python (2 commands). From spideynolove/memory.
olgasafonova/productplan-mcp-server
Hook Claude Code
One of 3 in settings.json
Runs before the context is compacted, running bd prime. From olgasafonova/productplan-mcp-server.
olgasafonova/productplan-mcp-server
Hook Claude Code
One of 3 in settings.json
Runs when a session starts, running bd prime. From olgasafonova/productplan-mcp-server.
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 before the agent uses a tool for Bash tool calls, executing guard-release-notes.sh via sh. From RikaiDev/yomi.
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
One of 4 in hooks.json
Runs when the agent finishes a response, executing stop-observer.cjs via node. From ShipToday/forge-plugin-codex.
Hook
One of 4 in hooks.json
Runs before the agent uses a tool, executing workflow-guard.cjs via node. From ShipToday/forge-plugin-codex.
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: