io.github.KryptosAI/agent-observability MCP Server
io.github.KryptosAI/agent-observability
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.KryptosAI/agent-observability MCP server?
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
How to install io.github.KryptosAI/agent-observability
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"agent-observability": {
"command": "npx",
"args": [
"-y",
"agent-obs"
]
}
}
}Related MCP servers
MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF.

MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.

Helm MCP
Give your AI assistant access to real Helm chart data. No more hallucinated values.yaml files.

Kloakt
Cloaked headless browser for AI agents — stealth TLS, smart extraction, SPA fallback

Krystal Voice Caller
Drive a Krystal Voice Caller tenant from Claude, Cursor, or any MCP-aware agent.

KrystalView Analytics
Read-only MCP access to sessions, funnels, campaigns, errors, live visitors, and anomalies.