Agentic Observability MCP
Agent tracing, cost tracking, anomaly detection for LLM agents
Connector by mdfifty50-boop · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/mdfifty50-boop-agentic-observability
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 3 read · 1 write · 0 delete · 2 not yet classified
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Node.js package
Tools by what they do 6
Read from the source code; the running server may list different tools.
Read 3 · Look things up without changing anything.
detect_anomalyget_cost_reportget_session_summary
Write 1 · Create, change, send or run things.
log_tool_call
Not yet classified 2 · We could not tell from the name and description.
trace_agent_actiontrack_token_usage
Tools (6)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
detect_anomalyFlag unusual patterns in agent behavior: cost spikes, high error rates, latency issues, infinite loops, and token explosions.
get_cost_reportGet cost breakdown across multiple sessions, grouped by model, provider, tool, or session. Supports time range filtering.
get_session_summaryGet a comprehensive cost and performance summary for an agent session, including token usage, tool call stats, and model breakdown.
log_tool_callLog an MCP tool call with performance data including latency, success/failure, and error details.
trace_agent_actionLog an agent action with metadata for audit trails and debugging. Supports tool calls, LLM requests, decisions, and errors.
track_token_usageTrack token usage and cost for an LLM call. Auto-calculates cost from built-in pricing table if per-token costs are not provided.
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit
- Apr 24, 2026 (6 months ago)
- Last release
- Apr 23, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.mdfifty50-boop/agentic-observability- Version
- 0.1.1
- Auth
- No auth
- Packages
- npm agentic-observability-mcp
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from mdfifty50-boop
- 0.444score
A2A Bridge
mdfifty50-boop
Agent-to-agent communication bridge for multi-agent systems
ConnectorDFreshness: DLocal★ 1Claude Code +5 - 0.423score
Compliance Shield
mdfifty50-boop
ZATCA, UAE CT, EU AI Act regulatory compliance for AI agents
ConnectorDFreshness: DLocalClaude Code +5 - 0.423score
Gcc Intelligence
mdfifty50-boop
GCC regulatory intelligence, ZATCA e-invoicing, and Arabic NLP for AI agents
ConnectorDFreshness: DLocalClaude Code +5 - 0.420score
Agent Replay
mdfifty50-boop
Record and replay AI agent execution for debugging
ConnectorDFreshness: DLocalClaude Code +5 - 0.420score
Secure Vault
mdfifty50-boop
Encrypted secrets and credential management for agents
ConnectorDFreshness: DLocalClaude Code +5 - 0.420score
Scope Guard
mdfifty50-boop
Hard scope boundaries to prevent AI agent drift
ConnectorDFreshness: DLocalClaude Code +5
Cite this page
Agentic Observability MCP. Agent Mart. https://agentmart.dev/connectors/mdfifty50-boop-agentic-observability (last updated 2026-10-24)