Lgtm MCP

LGTM Stack (Alertmanager and Grafana) system observability orchestrator. Built with the highest architectural standards, incorporating dynamic facades, custom API routing, and FastMCP tool decoration.

Documentation — Installation, deployment, usage across the API and MCP interfaces, and guidance for provisioning the LGTM observability stack are maintained in the official documentation.

Table of Contents

• Overview
• Features
• Installation
• Usage
• Configuration
• MCP Tools
• Architecture
• Deployment
• Documentation
• Contributing
• License

---

Overview

Lgtm MCP provides a high-performance, model-optimized interface to Lgtm capabilities. It isolates the model from underlying API transport complexity, ensuring safe, idempotent, and highly traceable system interactions.

---

Features

• Dynamic Facade Orchestration: Integrates multi-inheritance clients cleanly under a single facade.
• Battle-Tested Resilience: Out-of-the-box credential authentication, connection polling, and request retry strategies.
• FastMCP Declarative Tools: Fast, native schema registration with full inline validation.
• Complete Test Intent Diversity: Deep, automated unit, integration, and mock tests ensuring high code coverage.

---

⚙️ Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows the operator to restrict the set of exposed tools to prevent blowing up the LLM's context window.

The operator can configure tool filtering via multiple input channels:

• CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
• Environment Variables: Define standard environment variables:
  • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
  • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
• HTTP SSE Request Headers: Pass custom headers during transport initialization:
  • x-mcp-enabled-tools / x-mcp-disabled-tools
  • x-mcp-enabled-tags / x-mcp-disabled-tags
• HTTP SSE Request Query Parameters: Append query parameters directly to the operator's transport connection URL:
  • ?tools=tool1,tool2
  • ?tags=tag1

When query strings or parameters are provided, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.

---

Installation

Pick the extra that matches what the operator want to run:

Extra	Installs	Use when
lgtm-mcp[mcp]	Connector-focused MCP server (agent-connector-sdk[mcp] — FastMCP/FastAPI + epistemic-graph[full])	The operator only run the MCP server (smallest install / image)
lgtm-mcp[agent]	Agent runtime (agent-connector-sdk[agent-runtime,logfire] — model orchestration + epistemic-graph[full])	The operator run the integrated agent
lgtm-mcp[all]	Everything (mcp + agent + logfire)	Development / both surfaces

# Connector-focused MCP server (includes the shared graph engine)
uv pip install "lgtm-mcp[mcp]"

# Agent runtime (adds model orchestration to the shared graph engine)
uv pip install "lgtm-mcp[agent]"

# Everything (development)
uv pip install "lgtm-mcp[all]"      # or: python -m pip install "lgtm-mcp[all]"

Container images (:mcp vs :agent)

One multi-stage docker/Dockerfile builds two right-sized images, selected by --target:

Image tag	Build target	Contents	Entrypoint
example/lgtm-mcp:mcp	--target mcp	lgtm-mcp[mcp] — connector-focused, includes epistemic-graph[full]; no model-orchestration stack	lgtm-mcp
example/lgtm-mcp@sha256:<digest>	--target agent (default)	lgtm-mcp[agent] — agent runtime, model orchestration + epistemic-graph[full]	lgtm-agent

docker build --target mcp   -t example/lgtm-mcp:mcp    docker/   # connector-focused MCP server
docker build --target agent -t example/lgtm-mcp:agent-local docker/   # agent runtime

docker/mcp.compose.yml runs the connector-focused :mcp server; docker/compose.yml runs the agent (immutable agent digest) with a co-located :mcp sidecar.

Knowledge-graph database (epistemic-graph)

Both [mcp] and [agent] carry the epistemic-graph engine through the required Agent Utilities core dependency (epistemic-graph[full]). The [mcp] extra keeps the server connector-focused; [agent] also enables model orchestration. Local deployments can use the bundled engine. For production or shared state, run epistemic-graph as a dedicated database service and configure the runtime to use it. Deployment recipes (single-node + Raft HA), connection configuration, and architecture diagrams are documented in the epistemic-graph deployment guide.

---

Usage

The operator can start the FastMCP server in stdio mode via Python module execution:

import asyncio
from lgtm_mcp.mcp_server import get_mcp_instance


async def main():
    mcp = get_mcp_instance()
    # Execute stdio loop or launch server
    print("MCP Server ready.")


if __name__ == "__main__":
    asyncio.run(main())

For direct shell start, ran:

python -m lgtm_mcp.mcp_server

---

Environment Variables

Package environment variables

Variable	Example	Description
ALERTMANAGER_URL	http://localhost:9093	Prometheus Alertmanager server API URL
GRAFANA_URL	http://localhost:3000	Grafana server API endpoint
LGTM_TOKEN	secret-injected	Grafana admin API Key or Service Token
LGTM_MCP_BASE_URL	http://localhost	Fallback base URL used when ALERTMANAGER_URL / GRAFANA_URL are unset
LGTM_MCP_USERNAME	—	Basic-auth username (alternative to LGTM_TOKEN)
LGTM_MCP_PASSWORD	secret-injected	Basic-auth password (alternative to LGTM_TOKEN)
TLS_PROFILE	private-ca	AgentConfig named transport profile
TLS_PROFILE_REF	secret://transport/provider	Direct runtime profile reference
TLS_PROFILES_REF	secret://transport/catalog	Named runtime profile catalog
ALERTMANAGERTOOL	True	These names match the authoritative "Toggle Env Var" column in the README MCP tools table (condensed action-routed surface).
GRAFANATOOL	True
LGTM_MCP_MCP_IMAGE	—	Operator-approved immutable image@sha256 reference for the MCP Compose service
LGTM_TLS_PROFILE	—	Optional LGTM-specific AgentConfig TLS selectors; verification stays mandatory
LGTM_TLS_PROFILE_REF	—

Inherited agent-connector-sdk variables (apply to every connector)

Variable	Example	Description
TRANSPORT	stdio	MCP transport: stdio | streamable-http | sse
HOST	127.0.0.1	Loopback bind host (set an authenticated ingress explicitly)
PORT	8000	Bind port (HTTP transports)
MCP_ENABLED_TOOLS	—	Comma-separated tool allow-list
MCP_DISABLED_TOOLS	—	Comma-separated tool deny-list
MCP_ENABLED_TAGS	—	Comma-separated tag allow-list
MCP_DISABLED_TAGS	—	Comma-separated tag deny-list
EUNOMIA_TYPE	none	Authorization mode: none | embedded | remote
EUNOMIA_POLICY_FILE	mcp_policies.json	Embedded Eunomia policy file
EUNOMIA_REMOTE_URL	—	Remote Eunomia authorization server URL
ENABLE_OTEL	False	Enable OpenTelemetry export
OTEL_EXPORTER_OTLP_ENDPOINT	—	OTLP collector endpoint
MCP_CLIENT_AUTH	—	Outbound MCP child auth: oidc-client-credentials | basic | none
OIDC_CLIENT_ID	—	OIDC client id (service-account auth)
OIDC_CLIENT_SECRET_REF	secret://identity/oidc-client-secret	Runtime secret reference for the OIDC service account
MCP_BASIC_AUTH_USERNAME	—	HTTP Basic username (MCP_CLIENT_AUTH=basic)
MCP_BASIC_AUTH_PASSWORD_REF	secret://identity/mcp-basic-password	Runtime secret reference for HTTP Basic auth (MCP_CLIENT_AUTH=basic)
DEBUG	False	Verbose logging
PYTHONUNBUFFERED	1	Unbuffered stdout (recommended in containers)
MCP_URL	http://localhost:8000/mcp	URL of the MCP server the agent connects to
PROVIDER	—	Operator-configured LLM provider for the agent
MODEL_ID	—	Operator-configured model id for the agent
ENABLE_WEB_UI	True	Serve the AG-UI web interface

14 package + 23 inherited variable(s). Auto-generated from .env.example + the shared agent-connector-sdk set — do not edit.

Every variable the server reads. A local template is provided inside .env.example — copy it to .env and fill in the operator's endpoints/credentials.

Connection & Credentials

Variable	Description	Default
ALERTMANAGER_URL	Prometheus Alertmanager server API URL	http://localhost:9093
GRAFANA_URL	Grafana server API endpoint	http://localhost:3000
LGTM_TOKEN	Grafana admin API Key or Service Token	—

MCP server / transport

Variable	Description	Default
TRANSPORT	stdio, streamable-http, or sse	stdio
HOST	Bind host (HTTP transports)	0.0.0.0
PORT	Bind port (HTTP transports)	8000
MCP_TOOL_MODE	Tool surface: condensed, verbose, or both	condensed
MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS	Comma-separated tool allow/deny list	—
MCP_ENABLED_TAGS / MCP_DISABLED_TAGS	Comma-separated tag allow/deny list	—
DEBUG	Verbose logging	False
PYTHONUNBUFFERED	Unbuffered stdout (recommended in containers)	1

Tool toggles

Each action-routed tool can be disabled individually via its toggle env var (set to false). The full list is in the MCP Tools table above (ALERTMANAGERTOOL, GRAFANATOOL).

Agent CLI (full [agent] runtime only)

Variable	Description	Default
MCP_URL	URL of the MCP server the agent connects to	http://localhost:8000/mcp
PROVIDER	LLM provider (e.g. openai)	openai
MODEL_ID	Model id (e.g. gpt-4o)	gpt-4o
ENABLE_WEB_UI	Serve the AG-UI web interface	True

---

MCP Tools

The following declarative FastMCP tools are registered and available to upstream AI agents:

Auto-generated — do not edit between the markers below.

Intent tools

MCP Tool	Kind	Description
lgtm_ingest_alerts	intent	Natively ingest Alertmanager alerts into epistemic-graph as typed :Alert nodes.
lgtm_ingest_dashboards	intent	Natively ingest Grafana dashboards into epistemic-graph as typed :Dashboard nodes.
lgtm_mcp_alertmanager	intent	Manage LGTM MCP Alertmanager operations.
lgtm_mcp_grafana	intent	Manage LGTM MCP Grafana operations.

4 intent tool(s) · 0 operation(s). Call an operation as act(action='<operation>', params={...}) (ask for reads); find(action='describe', params={'action': '<operation>'}) returns its arguments. An operation is enabled unless its <DOMAIN>TOOL toggle is set false. Auto-generated — do not edit.

See docs/overview.md or docs/concepts.md for deeper operational examples.

---

MCP Configuration Examples

Install the connector-focused [mcp] extra. Examples use lgtm-mcp[mcp] to add FastMCP / FastAPI through agent-connector-sdk[mcp]; the required Agent Utilities core still carries epistemic-graph[full]. The [agent-runtime] extra additionally enables model orchestration.

stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

{
  "mcpServers": {
    "lgtm-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "lgtm-mcp[mcp]",
        "lgtm-mcp"
      ],
      "env": {
        "ALERTMANAGERTOOL": "True",
        "ALERTMANAGER_URL": "http://localhost:9093",
        "GRAFANATOOL": "True",
        "GRAFANA_URL": "http://localhost:3000",
        "LGTM_MCP_BASE_URL": "http://localhost",
        "LGTM_TOKEN": "your_grafana_api_token"
      }
    }
  }
}

Runtime references require an alias-aware launcher such as Arbora. Other launchers must omit those entries and inject the resolved values through their own runtime secret boundary.

Streamable-HTTP Transport (networked / production)

{
  "mcpServers": {
    "lgtm-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "lgtm-mcp[mcp]",
        "lgtm-mcp",
        "--transport",
        "streamable-http",
        "--port",
        "8000"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "127.0.0.1",
        "PORT": "8000",
        "ALERTMANAGERTOOL": "True",
        "ALERTMANAGER_URL": "http://localhost:9093",
        "GRAFANATOOL": "True",
        "GRAFANA_URL": "http://localhost:3000",
        "LGTM_MCP_BASE_URL": "http://localhost",
        "LGTM_TOKEN": "your_grafana_api_token"
      }
    }
  }
}

Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:

{
  "mcpServers": {
    "lgtm-mcp": {
      "url": "http://localhost:8000/lgtm-mcp/mcp"
    }
  }
}

Run a reviewed container image as a least-privilege stdio child (no listener or published port):

docker run -i --rm \
  --read-only \
  --cap-drop=ALL \
  --security-opt=no-new-privileges \
  --pids-limit=256 \
  --tmpfs /tmp:rw,noexec,nosuid,nodev,size=64m \
  -e TRANSPORT=stdio \
  -e ALERTMANAGERTOOL=True \
  -e ALERTMANAGER_URL=http://localhost:9093 \
  -e GRAFANATOOL=True \
  -e GRAFANA_URL=http://localhost:3000 \
  -e LGTM_MCP_BASE_URL=http://localhost \
  -e LGTM_TOKEN=your_grafana_api_token \
  registry.example.invalid/lgtm-mcp@sha256:<digest> lgtm-mcp

For containerized network HTTP, supply an authenticated TLS ingress (or direct server TLS), exact MCP_ALLOWED_HOSTS, and an exact trusted-proxy CIDR policy through the operator-owned deployment profile. The generator does not emit an unauthenticated non-loopback listener.

Auto-generated from the code-read env surface (package vars) — do not edit.

Architecture

This package uses the standardized Agent-Utilities dynamic facade architecture:

graph TD
    User([User Agent]) --> Server[FastMCP Server]
    Server --> Facade[Api Dynamic Facade]
    Facade --> ClientBase[ApiClientBase]
    Facade --> Auth[Credentials Auth Handler]
    ClientBase --> Service([External Service API])

---

Deployment

Bare-Metal (Standard pip)

1. Set up the operator's Python virtual environment (>= 3.10).
2. Install the package: pip install .[all]
3. Export credentials:

   export LGTM_URL="http://localhost:3000"
   

4. Run: python -m lgtm_mcp.mcp_server

Container (Docker Compose)

A standard compose structure is provided inside the docker/ folder. Build and deploy:

docker compose -f docker/compose.yml up --build -d

---

Additional Deployment Options

lgtm-mcp can run as a local stdio process or container, or behind a remote network boundary. The Deployment guide carries the detailed transport contract.

• Local container — launch a reviewed immutable image as a least-privilege stdio child with no listener or published port.
• Remote URL — connect through an operator-supplied authenticated HTTPS ingress. Keep its URL, outbound identity references, trust profile, and exact MCP_ALLOWED_HOSTS in AgentConfig.

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

Page	Contents
Installation	pip, source, extras, prebuilt Docker image
Deployment	run the MCP server, the agent server, Compose, Caddy + Technitium, env config
Usage	the MCP tools and the Api Python client
Backing Platform	deploy the LGTM observability stack with Docker
Overview	architecture and the dynamic facade
Concepts	concept registry (CONCEPT:LGTM-*)

---

Contributing

Please audit all code changes against the repository's contribution and review requirements, and run:

pre-commit run --all-files

---

License

This project is licensed under the MIT License. See the LICENSE file for complete details.

Deploy with agent-connector-sdk-deployment

Provision this package with the consolidated agent-connector-sdk-deployment workflow. It selects an installed-package, editable-source, or immutable-container path; records only runtime secret and TLS-profile references in AgentConfig; and runs doctor, registration, policy, observability, and rollback gates. Ask your agent to "deploy lgtm-mcp with agent-connector-sdk-deployment".

Install mode	Command
Installed package	uv tool install "lgtm-mcp[mcp]", then run lgtm-mcp
Editable source	uv pip install -e ".[agent]", then run lgtm-mcp
Immutable container	deploy registry.example.invalid/lgtm-mcp@sha256:<digest> through the operator-selected orchestrator

The repository embeds no deployment profile, credential value, certificate path, or environment-specific endpoint. Supply those at runtime through AgentConfig and the configured secret provider.

Governed capability contract

This package ships a compact canonical skill surface with specialist procedures kept as referenced workflows. The current MCP tools, skill metadata, connector_manifest.yml, ontology, mappings, shapes, fixtures, migrations, tool-schema fingerprints, and certification metadata form one versioned capability contract. Validate them together; do not rely on stale tool names or historical per-task skill wrappers.

Runtime endpoints, credentials, certificate trust, tenant identity, retention, and observability policy are deployment inputs and are never packaged values. See Configuration, trust, and privacy before enabling a network transport, connector ingestion, Arbora delegation, or trace export.