mcpField
A

Agent Observability

Local
@blueskylineassetsData & Analytics

About Agent Observability

Agent observability: structured logging, cost tracking, and compliance audit trails

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "blueskylineassets-agent-observability": {
      "command": "npx",
      "args": [
        "-y",
        "agent-observability-mcp"
      ],
      "env": {
        "AGENT_OBS_API_KEY": "<AGENT_OBS_API_KEY>",
        "AGENT_OBS_API_URL": "<AGENT_OBS_API_URL>"
      }
    }
  }
}
Run commandnpx -y agent-observability-mcp
Environment variables to set
AGENT_OBS_API_KEYSecretAPI key for the Agent Observability service (get one at POST /v1/register)
AGENT_OBS_API_URLURL of the Agent Observability API (defaults to https://api-production-0c55.up.railway.app)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmagent-observability-mcp1.1.0

Tools

3

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
agent_idstringNoIdentifier for the agent generating this log
metadataobjectNoStructured metadata: provider, cost_usd, latency_ms, tokens_used, model, etc.
severityenumNoEvent severity level (default: info)debug | info | warning | error | critical
event_typestringYesType of event: 'api_call', 'decision', 'transaction', 'error', 'state_change'

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.