Developer · Local MCP server
Agent Observability
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.KryptosAI/agent-observability- Version
- 1.0.7
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-07-24
- Updated
- 2026-07-24
- Publisher
- KryptosAI (GitHub) · 3 servers with pages here
- Repository
- github.com/KryptosAI/agent-observability
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | agent-obs | 1.0.7 | stdio |
How to connect Agent Observability
Agent Observability runs locally from a Node.js package published to the npm registry: agent-obs version 1.0.7. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y agent-obs@1.0.7.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"agent-observability": {
"command": "npx",
"args": [
"-y",
"agent-obs@1.0.7"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from KryptosAI (GitHub)
| Server | Runs |
|---|---|
| MCP ObservatoryMCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF. | Local · stdio |
| MCP SeatbeltMCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine. | Local · stdio |
More developer servers
| Server | Runs |
|---|---|
| Agent Memory MCPAgent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops. | Local · stdio |
| Agent Memory MCPMarkdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database. | Local · stdio |
| Agent Never Give UpAn escape guide for coding agents, providing structured thinking tools to help agents unstick. | Local · stdio |
| Agent Nexus180+ tested APIs, MCP servers and CLIs your agent can call. Self-service key in one call. | Remote · HTTP |
| Agent ObservabilityAI agent observability with deterministic record/replay for debugging agent failures. | Local · stdio |
| Agent Output GuardValidate and verify data from other agents before acting on it. Zero LLM costs. | Local · stdio |
| Agent PlanetsA galaxy where every AI agent owns a planet: claim free, terraform, build, visit, trade. | Remote · HTTP |
| Agent Readiness AuditorAudits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt. | Local · stdio |