mcp-parseable-server
About
MCP server for Parseable observability platform
Details
- Author
- thenodon
- Categories
- Database
Jump to
Setup
Install mcp-parseable-server in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/thenodon/mcp-parseable-server
Follow the installation instructions in the repository README, then restart your MCP client.
mcp-parseable-server - A Parseable MCP Server
This project is currently in early development with focus on log data. Feedback and contributions are welcome.
- vscode with Github Copilot as the agent.
- opencode agent CLI tool
This project provides an MCP (Message Context Protocol) server forParseable, enabling AI agents and tools to interact with Parseable data streams (logs, metrics, traces) using natural language and structured tool calls.
- List available data streams in Parseable
- Query data streams using SQL
- Get schema, stats, and info for any data stream
- Modular MCP tool registration for easy extension
- Supports both HTTP and stdio MCP modes
- Environment variable and flag-based configuration
- The mcp server returns responses in json where the payload is both in text and structured format.
In Parseable dataset and data stream names are used interchangeably, as Parseable's datasets are essentially named data streams. In all tool description we try to use the term data stream to avoid confusion with the term dataset which can have different meanings in other contexts.
The mcp server does not implement any authentication mechanisms. If this is needed, use a reverse proxy like nginx or envoy in front of the mcp server to add authentication and authorization.
The mcp server does not implement any session management since all tool calls are stateless. This may change in the future.
git clone https://github.com/thenodon/mcp-parseable-server cd mcp-parseable-server # Build the MCP server binary go build -o mcp-parseable-server ./cmd/mcp_parseable_server
The MCP server will listen onhttp://localhost:9034/mcpfor agent/tool requests.
This mode is used for CLI or agent-to-agent workflows.
You can configure the Parseable connection using environment variables or flags:
- PARSEABLE_URLor--parseable-url- url to the parseable instance (default:http://localhost:8000)
- PARSEABLE_USERNAMEor--parseable-user(default: admin)
- PARSEABLE_PASSWORDor--parseable-pass(default: admin)
- LISTEN_ADDRor--listen- the address when running the mcp server in http mode (default: :9034)
- INSECURE- set totrueto skip TLS verification (default: false)
- - set log level. Supported levels are debug, info, warn and error (default: info)
PARSEABLE_URL="http://your-parseable-host:8000" PARSEABLE_USER="admin" PARSEABLE_PASS="admin" ./mcp-parseable-server
For production deployment use a reverse proxy like nginx or envoy in front of the mcp server that manages authentication, authorization, and tls termination.
SeeTESTING.mdfor a complete testing guide.
Execute a SQL query against a data stream.
- Inputs:
- query: SQL query stringstreamName
- : Name of the data streamstartTime
- : ISO 8601 start time (e.g. 2026-01-01T00:00:00+00:00)endTime
- : ISO 8601 end time
List all available data streams in Parseable.
- Returns:Array of stream objects with count
Get the fields schema for a specific data stream.
- Inputs:
- stream: Name of the data stream
- Inputs:
- streamName: Name of the data stream
- Inputs:
- streamName: Name of the data stream
- Returns:About object (see tool description for details)
- Returns:Roles object (see tool description for details)
The server provides 5 pre-built prompts for common workflows:
- analyze-errors- Find and analyze error logs
- stream-health-check- Perform comprehensive health assessment
- investigate-field- Deep dive into field values and distributions
- compare-streams- Compare metrics across multiple streams
- find-anomalies- Detect unusual patterns and anomalies
For detailed documentation and examples, seePROMPTS_GUIDE.md.
Agents can discover all available tools and their input/output schemas via the MCP protocol. Each tool description includes details about returned fields and their meanings.
To add new tools, create a new file intools/, implement the registration function, and add it toRegisterParseableToolsintools/register.go.
curl -u admin:<password> http://localhost:8000/api/v1/about
- Reduce query time range
- Add LIMIT clauses to SQL queries
- Check if Parseable is responsive
- Verify streams exist: ask agent to "list all streams"
- Check stream names are exact matches (case-sensitive)
- Verify Parseable has data in the streams
- Stream name exists and has data
- Time range includes actual events
- PARSEABLE_URL, USER, PASS are correct
- Check that time range contains data
- Verify PARSEABLE_USER has permissions for the streams
- Use agent's troubleshooting capabilities to debug
- Port 9034 is available (for HTTP mode)
- Environment variables are set
- Go version is 1.20+ (go version)
This work is licensed under the GNU GENERAL PUBLIC LICENSE Version 3.
- No resources are currently included for agent usage (prompts are implemented).
- No tools to understand the Parseable setups. It can by using theabout`tool understand if cluster or standalone, but nothing about the configuration.
Official Airtable MCP server and skills for working with bases, records, workflows, and business operations from AI agents.
MCP Server For Apache Doris, an MPP-based real-time data warehouse.
Official MCP Server from Atlan which enables you to bring the power of metadata to your AI tools
Query Onchain data, like ERC20 tokens, transaction history, smart contract state.
Read and write access to your Baserow tables.
Introspect and query your apps deployed to Convex.
Interact with the data stored in Couchbase clusters using natural language.
Maritime intelligence for tracking vessels, analysing ports, and exploring ship data.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
