Clerk

data-ai MCP Server

Auto-summarize Claude Code sessions as local markdown — session summaries, keyword index, on-demand reports.

Verified
data-aidata-ai
4 views31 stars1 forksGPL-3.0

Why This Matters

Discovered via github-topic:mcp and last synced 3mo ago.

Verified
Source
github-topic:mcp
Stars
31
Last synced
3mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
39
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (39)

status

Show active feed processes and interrupted sessions

punch

Record session ID on session start

5m

Timeout for API calls (e.g. 5m, 2m30s, 1h)

Platform

Command

unregister

Unregister clerk from Claude Code

Key

Default

clerk-index-read

Read the content of one or more index terms

hook

B[clerk punch] C[Session End] -->

report

Generate a report and auto-save to `reports/` (piped: stdout)

Command

Description

install

`register`

Tool

Description

config

Show current configuration (alias for `config show`)

feed

Process session transcript and generate summary

en

Summary output language

Skill

Description

API

Command

logs

Show logs for troubleshooting

uninstall

`unregister`

clerk-resume

Returns summary + transcript file paths for context recovery

register

Register clerk with Claude Code and verify environment

version

Show current version and check for updates

diagnosis

`register`

clerk-index-list

List all available index terms (tags, dates, projects, keywords)

Event

What happens

export

List available slugs and dates (alias for `list`)

Old

New

true

Enable/disable feed for this project

MCP

F I["/clerk-search"] -->

list

List available slugs and dates

mcp

Start MCP stdio server

30

Days to keep log and cursor files

provider

List supported AI providers with default settings

ollama

`http://localhost:11434/v1`

claude

(CLI, no endpoint needed)

gemini

`https://generativelanguage.googleapis.com/v1beta/openai`

Provider

Endpoint

groq

`https://api.groq.com/openai/v1`

openai

`https://api.openai.com/v1`