agent-store
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., "@agent-storelist services with error counts in the last 24h"
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.
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.tsRelated MCP server: openobserve-community-mcp
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 testEnv vars
Var | Default | Description |
|
| HTTP listen port |
|
| MCP endpoint path |
| — | Full postgres URL (overrides PGHOST etc.) |
|
| Postgres host |
|
| Postgres port |
|
| Postgres user |
|
| Postgres password |
|
| Postgres database |
|
| Directory for ingest audit JSONL files |
Routes
Method | Path | Description |
|
| OTLP/JSON trace ingest |
|
| OTLP/JSON log ingest |
|
| OTLP/JSON metric ingest |
|
| Health check (includes PG ping) |
|
| MCP streamable-http |
Schema (telemetry schema, auto-migrated on startup)
telemetry.spans— OTLP trace spans with resource/scope/attributes as JSONBtelemetry.logs— OTLP log recordstelemetry.metrics— OTLP metric datapoints (gauge/sum/histogram decomposed)
MCP tools
Tool | Description |
| Filter logs by service, body, severity, time range |
| Trace summaries (root span, count, duration, error flag) |
| All spans for a trace_id, parent-child reconstructable |
| Pre-aggregated per-service stats: spans, errors, top names, daily |
| All services with span/log counts and last_seen |
| 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-storeThis server cannot be deployed
Maintenance
Related MCP Connectors
- SuperlogOAuthsh.superlog
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
Versioned agent memory in your own Postgres: portable context, permissioned, audit trail.
- FixterOAuthdev.fixter
Monitoring for small teams. Logs, traces, metrics, live issue tracking, API/MCP uptime.
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
Related MCP Servers
- AlicenseAqualityAmaintenanceMCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.9209 npm9MIT
- AlicenseBqualityCmaintenanceA read-only MCP server for OpenObserve Community Edition that works over the REST API. Provides tools for searching logs, traces, stream schemas, and dashboards - no Enterprise license required.8196 PyPI16GPL 3.0
- AlicenseAqualityAmaintenanceUnified observability gateway for AI agents — one MCP server for Prometheus, Loki, and any backend.126Apache 2.0
- AlicenseAqualityAmaintenanceTransparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server, persist traces to SQLite · Postgres · MySQL. No code changes needed.211 npm11Apache 2.0