MCP Servers

agent-store

Minimal agent telemetry store with OTLP/HTTP ingestion to Postgres and MCP streamable-http tools for querying logs, traces, and metrics.

README

agent-store

Minimal agent telemetry store. One process, two paths:

OTLP/HTTP (JSON encoding) → ingest spans/logs/metrics → Postgres
MCP streamable-http → query Postgres → agent introspection tools

Quick start

# Local dev
PGHOST=localhost PGPORT=5432 PGUSER=postgres PGPASSWORD=secret PGDATABASE=agentstore \
  bun run src/server.ts

Testing

# Unit tests only (no DB)
bun test test/otlp-parse.test.ts

# Full integration tests (spins up docker postgres)
bash scripts/test-db.sh

# Or if PG is already running:
PGHOST=localhost PGPORT=5432 PGUSER=postgres PGPASSWORD=secret PGDATABASE=agentstore_test \
  bun test

Env vars

Var	Default	Description
`PORT`	`4318`	HTTP listen port
`MCP_PATH`	`/mcp`	MCP endpoint path
`DATABASE_URL`	—	Full postgres URL (overrides PGHOST etc.)
`PGHOST`	`localhost`	Postgres host
`PGPORT`	`5432`	Postgres port
`PGUSER`	`postgres`	Postgres user
`PGPASSWORD`	`postgres`	Postgres password
`PGDATABASE`	`agentstore`	Postgres database
`AUDIT_DIR`	`./data`	Directory for ingest audit JSONL files

Routes

Method	Path	Description
`POST`	`/v1/traces`	OTLP/JSON trace ingest
`POST`	`/v1/logs`	OTLP/JSON log ingest
`POST`	`/v1/metrics`	OTLP/JSON metric ingest
`GET`	`/healthz`	Health check (includes PG ping)
`ALL`	`/mcp`	MCP streamable-http

Schema (`telemetry` schema, auto-migrated on startup)

telemetry.spans — OTLP trace spans with resource/scope/attributes as JSONB
telemetry.logs — OTLP log records
telemetry.metrics — OTLP metric datapoints (gauge/sum/histogram decomposed)

MCP tools

Tool	Description
`query_logs`	Filter logs by service, body, severity, time range
`query_traces`	Trace summaries (root span, count, duration, error flag)
`get_trace`	All spans for a trace_id, parent-child reconstructable
`summarize_activity`	Pre-aggregated per-service stats: spans, errors, top names, daily
`list_services`	All services with span/log counts and last_seen
`service_schema`	Distinct span names + attribute keys for a service

since param accepts relative ("7d", "24h", "30m") or ISO datetime.

Docker

docker build -t agent-store .
docker run -e PGHOST=... -e PGPASSWORD=... -p 4318:4318 agent-store

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured