Best Attribution AI Skills & MCP Servers

MCP server for per-agent cost attribution, budget management, and spend analytics across AI agent fleets

AI-powered FastMCP server for intelligent stock photo search, download, and attribution management from Unsplash

Log10x MCP Server — per-pattern log cost attribution, root-cause investigation, pasted-batch triage, archive query/backfill, and cross-pillar correlation against customer metric backends (Grafana Cloud, Mimir, Thanos, AMP) with structural validation that

MCP server for the Agent Passport System — protocol-layer tools only. 150 tools (132 protocol + 10 gateway deprecation stubs). Identity, delegation, reputation, attestation, coordination, commerce, attribution primitive, attribution settlement. Tracks SDK

MCP server for the Syndicate Links affiliate commission API - 11 tools for AI agent attribution, program discovery, publisher link creation, and commission tracking

MCP server for atrib. The producer-side cognitive primitive: lets agents sign explicit observations, annotations, and revisions beyond what middleware auto-signs.

MCP server for atrib. Lets agents mark a past record's importance and meaning. Adds an ANNOTATES graph edge so recall surfaces weighted annotations ahead of flat scans.

MCP server middleware for atrib. Signed receipts for every tool call, one-line integration.

MCP server for atrib. Lets agents supersede a prior signed position with a stated reason. Adds a REVISES graph edge so the contradiction is a first-class node rather than a silent edit.

MCP server for atrib. Lets agents query their own provable past from the local signed-record mirror with per-record signature verification.

Verifier library for atrib. Independent signature, graph-derivation, and settlement-recommendation checks per atrib spec §4.6.

Generic config-driven MCP wrapper for atrib. Spawns any upstream MCP server and applies @atrib/mcp middleware so every tool call is signed and logged. Wrap any MCP via JSON config, no per-server code.

MCP server for atrib. Synthesizes a narrative across N records via an OpenAI-compatible LLM so agents read context, not raw record bytes.

Agent middleware for atrib. Interceptor plus framework adapters for MCP attribution. Supports raw SDK, Claude Agent SDK, Cloudflare Agents, Vercel AI SDK, LangChain JS.

MCP server for atrib. Walks informed_by chains backward from a record_hash to surface the reasoning chain that produced it.

MCP server for ctscout.dev — domain attribution via Certificate Transparency + multi-signal Pro enrichment