Parseable MCP Server
OfficialAllows creating and managing Slack alert targets for Parseable alerts, enabling notifications to be sent to Slack channels.
Click on "Install 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., "@Parseable MCP Servershow me the last 100 error logs from the production dataset"
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.
Parseable MCP Server
Model Context Protocol server for Parseable. Lets any MCP-capable client (Claude Desktop, Claude Code, Cursor, VS Code Copilot, Windsurf, Continue, Cline, Zed, Codex) discover, query, and manage Parseable datasets and alerts using natural language.
Two transports:
Mode | Transport | Auth | Use when |
| Stdin/stdout | API key via env vars | Claude Desktop, Cursor, VS Code, local clients |
| Streamable HTTP | Cloud API key, or self-hosted URL + API key | Hosted deployments and remote clients |
Quickstart — stdio (local)
One command — interactive setup, detects Claude Desktop / Cursor, writes config files:
npx -y @parseable/parseable-mcp-server initRestart your MCP client. Tools appear. Done.
Scripted:
npx -y @parseable/parseable-mcp-server init \
--client claude-desktop \
--url https://your-parseable.example.com \
--api-key "$PARSEABLE_API_KEY"Supported --client values: claude-desktop, cursor.
Related MCP server: Agent Construct
Quickstart — HTTP (hosted)
HTTP mode serves a setup page and MCP endpoint from one process. Cloud clients supply an API key. Self-hosted clients supply their Parseable URL and API key.
1. Set env vars
# .env
PORT=87872. Run
# From source
npm run build:all
node dist/server.js http
# Docker
docker build -t parseable-mcp-server .
docker run -p 8787:8787 --env-file .env parseable-mcp-server3. Connect from Claude
Claude Desktop → Settings → Connectors → Add custom connector
Name:
ParseableURL:
https://mcp.your-domain.com/mcpHeader
X-Parseable-URL:https://your-parseable.example.comHeader
X-API-Key: your Parseable API keyClick Add → Connect
4. Connect from Claude Code
claude mcp add --transport http parseable https://mcp.your-domain.com/mcp --scope user \
--header "X-Parseable-URL: https://your-parseable.example.com" \
--header "X-API-Key: $PARSEABLE_API_KEY"5. Connect from Cursor / VS Code
{
"mcpServers": {
"parseable": {
"type": "http",
"url": "https://mcp.your-domain.com/mcp",
"headers": {
"X-Parseable-URL": "https://your-parseable.example.com",
"X-API-Key": "your-parseable-api-key"
}
}
}
}HTTP authentication
Each POST /mcp request requires X-API-Key and supports two modes:
Mode | Headers |
Cloud |
|
Self-hosted (default) |
|
X-Parseable-Mode is checked first when present. Omitting it selects self-hosted mode; clients do not need to send X-Parseable-Mode: self-hosted. In cloud mode, server validates API key with Parseable Cloud, caches returned URL and tenant routing in a bounded in-memory LRU for 24 hours, and sends x-p-tenant on Parseable requests. Cache is disposable; misses and process restarts resolve through Cloud again.
For self-hosted mode, HTTP server validates supplied URL and forwards API key to that Parseable instance. By default, private and loopback Parseable URLs are rejected to limit SSRF. Set PARSEABLE_MCP_ALLOW_PRIVATE=true only for trusted deployments that need private network targets.
Environment variables
stdio mode
Var | Required | Default | Purpose |
| ✅ | — | Parseable base URL |
| ✅ | — | API key for self-hosted Parseable |
| — | Advisory default dataset | |
| 1000 | Hard cap on query rows | |
| 30000 | HTTP timeout (ms) |
HTTP mode
Var | Required | Default | Purpose |
| 8787 | HTTP listen port | |
| false | Permit private/loopback Parseable URLs supplied in request headers | |
| Cloud only | - | Parseable Cloud orchestrator base URL |
| Cloud only | - | Service bearer token for API-key validation |
| 86400 | Cloud routing LRU TTL | |
| 10000 | Maximum cached cloud API-key routes | |
| 10000 | Cloud validation timeout |
OpenTelemetry (optional)
Var | Default | Purpose |
| false | Enable trace export to Parseable |
| — | Parseable OTLP endpoint |
| — | Basic auth for OTLP |
| — | Basic auth for OTLP |
| mcp-traces | Stream name for traces |
| false | Log OTLP export errors |
Copy .env.example → .env for a full template.
Tools
Discovery
Tool | Purpose |
| List all log datasets |
| Column names + types |
| Metadata (created_at, retention, time window) |
| Event count and storage bytes |
| Most recent N events (time-bounded, row-capped) |
Query
Tool | Purpose |
| SQL |
| PromQL instant or range query against a metrics dataset |
Alerts
Tool | Purpose |
| List all alerts with state, severity, tags |
| Full config for one alert |
| All alert tags in use |
| Enable an alert |
| Disable an alert |
| Force-evaluate now. May fire real notifications. |
| Create alert via guided Q&A (8 questions, confirms before submit) |
Alert targets
Tool | Purpose |
| List targets (Slack, webhook, Alertmanager) |
| Full config for one target |
| Create a new Slack / webhook / Alertmanager target |
Diagnostics
Tool | Purpose |
| Check connectivity, return version + health |
|
|
RBAC (read-only)
Tool | Purpose |
| List all users |
| Roles for a specific user |
| All role names |
| Privilege definition for a role |
| Default role for new users |
Admin (read-only)
Tool | Purpose |
| All nodes with status (distributed mode) |
| Aggregated ingest/query/storage metrics |
| Retention policy for a dataset |
Client setup — stdio
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"Parseable": {
"command": "npx",
"args": ["-y", "@parseable/parseable-mcp-server"],
"env": {
"PARSEABLE_URL": "https://your-parseable.example.com",
"PARSEABLE_API_KEY": "your-api-key"
}
}
}
}Claude Code
claude mcp add Parseable \
--env PARSEABLE_URL=https://your-parseable.example.com \
--env PARSEABLE_API_KEY=your-api-key \
-- npx -y @parseable/parseable-mcp-serverCursor
~/.cursor/mcp.json:
{
"mcpServers": {
"Parseable": {
"command": "npx",
"args": ["-y", "@parseable/parseable-mcp-server"],
"env": {
"PARSEABLE_URL": "https://your-parseable.example.com",
"PARSEABLE_API_KEY": "your-api-key"
}
}
}
}VS Code
.vscode/mcp.json:
{
"servers": {
"Parseable": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@parseable/parseable-mcp-server"],
"env": {
"PARSEABLE_URL": "https://your-parseable.example.com",
"PARSEABLE_API_KEY": "your-api-key"
}
}
}
}Development
git clone https://github.com/parseablehq/parseable-mcp-server.git
cd parseable-mcp-server
npm install
cp .env.example .env # fill in your values
# Build
npm run build # server only (tsc)
npm run build:ui # React UI only (vite)
npm run build:all # both
# Run
node dist/server.js # stdio mode
node dist/server.js http # HTTP mode (port 8787)
# Dev
npm run dev # tsc --watch
npm run dev:ui # vite dev server (proxies API to :8787)
npm test
npm run lint
npm run fix # biome auto-fixCI (GitHub Actions) runs lint + build:all + test on every push/PR to main on Node 22. On merge to main, Docker image is published to ghcr.io/parseablehq/parseable-mcp-server.
Security
Parseable API keys live in MCP client configuration. Use keys scoped to minimum required permissions.
HTTP clients send credentials in
X-Parseable-URLandX-API-Key; always use HTTPS for remote deployments.query_sqlblocks DDL/DML and enforces a rowLIMIT. Time window is mandatory.evaluate_alertcan fire real notifications — review the call before approving.No telemetry. Outbound calls go only to the Parseable instance configured by the user.
License
Apache-2.0. See LICENSE.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceA Model Context Protocol (MCP) server that supports STDIO, SSE and Streamable HTTP protocols for AI model interactions.Last updated371MIT
- Alicense-qualityDmaintenanceModel Context Protocol server that standardizes tool discovery, execution, and context management for AI applications.Last updatedMIT
- Alicense-qualityCmaintenanceA Model Context Protocol (MCP) server that provides MetricFlow CLI tools through both SSE and STDIO interfaces, enabling users to query metrics, list dimensions, and perform other MetricFlow operations via natural language.Last updated6MIT
- Alicense-qualityDmaintenanceEnables creating MCP (Model Context Protocol) servers with zero boilerplate, full TypeScript support, and multiple transports (stdio and HTTP).Last updated71MIT
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
MCP server for interacting with the Supabase platform
MCP (Model Context Protocol) server for Appwrite
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/parseablehq/parseable-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server