chatlab-mcp
The chatlab-mcp server manages ChatLab sessions and provides tools for querying, analyzing, and manipulating chat data via direct SQLite access or HTTP API.
Process Management
Start, stop, and check the status of the
chatlab-cliheadless HTTP serviceOpen the ChatLab Web UI for setup or interaction
Session Management
List, get metadata, and view overview statistics for imported chat sessions
Export sessions as ChatLab-format JSON and import JSON payloads into new or existing sessions
Message & Member Querying
Get paginated messages with optional filters (time range, keyword, sender)
List members within a session
Retrieve recent messages and context around a specific message
Search messages by keywords or exact substrings
Direct Database Access
Execute read-only SQL queries directly against a session's SQLite database (no HTTP service required)
Retrieve the SQLite schema of a session's database
Analytics
Analyze member activity rankings and time-based activity (hourly, weekday, daily)
Get conversation history between two specific members
Estimate response times within conversations
Perform keyword frequency analysis
List and retrieve conversation segment summaries and messages
Generic API Access
Make arbitrary HTTP API calls (GET, POST, PUT, DELETE, PATCH) to any ChatLab endpoint not covered by dedicated tools
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@chatlab-mcp list my chat sessions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
chatlab-cli-mcp
TypeScript MCP server for ChatLab. It combines direct SQLite analysis tools with chatlab-cli headless HTTP service management.
ChatLab CLI command used after local data exists:
chatlab start --headless --host 127.0.0.1 --port 3110 --token <token>On first run, when no ChatLab session database is found locally, the server starts ChatLab without --headless and allows the Web UI to open so you can import or configure data. After local data exists, startup does not open a browser automatically; use chatlab_open_ui when you want the page.
Install
Use directly with npx:
npx -y chatlab-cli-mcpOr install from source:
npm install
npm run buildRelated MCP server: wrapmcp
Configuration
Variable | Default | Description |
|
| ChatLab HTTP API port |
| empty | Fallback port variable if |
|
| ChatLab listen host |
| generated per MCP process | Bearer token passed to |
|
| ChatLab data root used by direct SQLite tools; databases live under |
|
| Start |
|
| Use |
|
| HTTP request timeout |
| bundled | Optional custom executable or script path |
MCP client example
{
"mcpServers": {
"chatlab": {
"command": "node",
"args": ["/home/projects/wechat-tool/chatlab-mcp/dist/index.js"],
"env": {
"CHATLAB_PORT": "3110",
"CHATLAB_TOKEN": "YOUR_TOKEN",
"CHATLAB_DATA_DIR": "/path/to/chatlab/data"
}
}
}
}After npm publish, you can use npx instead:
{
"mcpServers": {
"chatlab": {
"command": "npx",
"args": ["-y", "chatlab-cli-mcp"],
"env": {
"CHATLAB_PORT": "3110",
"CHATLAB_TOKEN": "YOUR_TOKEN",
"CHATLAB_DATA_DIR": "/path/to/chatlab/data"
}
}
}
}Tools
chatlab_start: startchatlab-clias a child process.chatlab_open_ui: start or restart with the Web UI enabled and open it in the browser.chatlab_stop: stop the child process started by this MCP server.chatlab_status: show process state and ChatLab/api/v1/status.chatlab_list_sessions: list imported chat sessions.chatlab_get_session: get one session's metadata.chatlab_get_messages: page messages from a session.chatlab_get_members: list members in a session.chatlab_get_overview: get session overview stats.chatlab_execute_sql: run readonly SQL directly against a session database.chatlab_get_schema: get the SQLite schema.chatlab_search_messages: search messages by keywords.chatlab_deep_search_messages: exact substring search.chatlab_get_recent_messages: fetch recent messages.chatlab_get_message_context: fetch context around a message.chatlab_get_member_stats: member activity ranking.chatlab_get_time_stats: hourly, weekday, or daily activity.chatlab_get_conversation_between: messages involving two members.chatlab_response_time_analysis: estimate response speed.chatlab_keyword_frequency: simple local keyword frequency.chatlab_get_segment_summaries: list generated conversation segments.chatlab_get_segment_messages: get messages in one segment.chatlab_export_session: export one session in ChatLab format.chatlab_import_session: import ChatLab-format JSON into a session ID.chatlab_request: call any ChatLab HTTP API endpoint.
Notes
ChatLab's default API port is
3110.Core reading and analysis tools access SQLite directly and do not require the HTTP service.
If no local session databases are found, auto-start opens the Web UI for first-time setup.
After local data exists, startup does not open the browser automatically; call
chatlab_open_uito open the page.The MCP server keeps ChatLab CLI logs on stderr so MCP stdio stays valid.
Import/export and custom API calls use
chatlab-cliheadless HTTP mode.
Available Tools
12 toolschatlab_execute_sqlB
Execute readonly SQL against a ChatLab session database.
Inputs: sql (required), sessionId (required).
chatlab_export_sessionB
Export one ChatLab session as ChatLab-format JSON.
Inputs: sessionId (required).
chatlab_get_membersC
List members in a ChatLab session.
Inputs: sessionId (required).
chatlab_get_messagesC
Get paginated messages from a ChatLab session.
Inputs: sessionId (required), page, limit, endTime, +3 more.
chatlab_get_overviewC
Get overview stats for a ChatLab session.
Inputs: sessionId (required).
chatlab_get_sessionA
Get metadata for one imported ChatLab session.
Inputs: sessionId (required).
chatlab_import_sessionC
Import a ChatLab-format JSON payload into a session ID.
Inputs: payload (required), sessionId (required).
chatlab_list_sessionsB
List imported ChatLab sessions.
Inputs: no named parameters.
chatlab_requestA
Call any ChatLab HTTP API endpoint. Use this for endpoints not covered by dedicated tools.
Inputs: path (required), body, query, method.
chatlab_startB
Start chatlab-cli in headless HTTP API mode. Port defaults to CHATLAB_PORT or 3110.
Inputs: host, port, headless.
chatlab_statusA
Get local process state and ChatLab API status.
Inputs: no named parameters.
chatlab_stopA
Stop the chatlab-cli child process started by this MCP server.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Each tool targets a distinct action—SQL execution, session export/import, listing, metadata retrieval, members, messages, overview, generic API call, and process management. No two tools have overlapping functionality, making it easy for an agent to select the correct one.
All tools use the 'chatlab_' prefix and snake_case. Most follow a verb_noun pattern (e.g., execute_sql, list_sessions), but 'chatlab_request' uses a noun as the verb, and the process commands (start, stop, status) omit a noun, breaking the pattern slightly.
With 12 tools, the set is well-scoped for managing ChatLab sessions: it covers session CRUD, data retrieval, SQL execution, process lifecycle, and a generic fallback. Neither too few nor too many for the domain.
The tools cover core session management (list, get, import, export, execute SQL, view members/messages/overview) and process control. Missing explicit update/delete operations, but the generic 'chatlab_request' tool can be used to fill gaps, preventing agent dead ends.
Related MCP Connectors
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server for managing Claude Code conversation sessions12MIT
- AlicenseNot gradedqualityCmaintenanceUniversal MCP server that wraps any CLI tool, enabling AI assistants to run commands via natural language.1MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for atest (api-testing), enabling natural language interaction with API testing workflows.8MIT
- AlicenseNot gradedqualityDmaintenanceMCP Server for interacting with the Langflow API via a natural language interface. It exposes Langflow functionalities as tools for LLMs.MIT