argo-watcher-mcp
Verified Safeby shini4i
Overview
Exposes Argo Watcher deployment history via the Model Context Protocol (MCP) to allow AI agents and other clients to query deployment data.
Installation
docker run --rm -p 8000:8000 -e ARGO_WATCHER_URL="http://host.docker.internal:8001" argo-watcher-mcpEnvironment Variables
- ARGO_WATCHER_URL
- HTTP_LISTEN_ADDR
- TRANSPORT_MODE
- REQUEST_TIMEOUT
- OTEL_ENABLED
- OTEL_SERVICE_NAME
- OTEL_EXPORTER_OTLP_ENDPOINT
- OTEL_EXPORTER_OTLP_INSECURE
- APP_NAME
- APP_VERSION
Security Notes
The project follows good security practices by externalizing sensitive configurations (like ARGO_WATCHER_URL and OTLP endpoints) through environment variables rather than hardcoding. It uses Go, a memory-safe language, which mitigates common vulnerabilities. OpenTelemetry is integrated, providing observability. The explicit `OTEL_EXPORTER_OTLP_INSECURE` flag allows control over TLS for OTLP connections, which is a conscious decision point for operators. No `eval` or similar dangerous patterns were found. Network risks are primarily associated with the configured `ARGO_WATCHER_URL` which, if compromised, could impact the integrity of the data served.
Similar Servers
mcp-k8s-go
This MCP server enables interaction with Kubernetes clusters to list, get, apply, and execute commands on various resources through a conversational interface.
mcp-for-argocd
Enables AI assistants to interact with Argo CD applications through natural language, streamlining DevOps tasks.
loki-mcp
A Go-based server that implements the Model Context Protocol (MCP) to integrate Grafana Loki log querying capabilities with AI agents like Claude Desktop or n8n.
mkp
MKP is a Model Context Protocol (MCP) server for Kubernetes, enabling LLM-powered applications to interact with Kubernetes clusters by providing tools for resource listing, getting, applying, deleting, and executing commands.