AI & Agent Tools MCP Servers

Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP

Google Search Console for AI agents: search analytics, sitemaps, URL inspection.

Trusted African data, provenance, citations, and catalog search for AI agents.

Real-time codebase graph for AI assistants: call graphs, dependencies, symbol lookup.

Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.

Multi-agent coordination MCP: claim work, survey peers, resolve conflicts via a git branch as CAS.

Multi-step web research with citations via Perplexity's Agent API. Standard library only.

Secure, fragment-based long-term memory for MCP-compatible AI agents.

F1 race engineer for Claude — 79 tools for live timing, telemetry, strategy, and 75 years of history

Windows desktop control for AI agents: screen, UI Automation, input, processes, files, shell.

Create, edit, validate, preview, and render Shotcut projects through AI clients.

Phylogenetic inference via IQ-TREE 2 — never returns a topology without its support

Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.

Thirty-two guarded agent utilities and maintained-data lookups over USDC x402.

Default trust layer for agentic payments: authorize agent spend, evidence, receipts, settlement.

End-to-end-encrypted, sovereign inbox for AI agents. The server only ever sees ciphertext.

Merged agent permission rules: which settings file wins, and which rules your client ignores.

What a checkout tells your agent to do: instruction files, hooks, declared MCP servers.

What fills your agent's context window before a session starts: skill descriptions, memory files.

Live OS ground truth for agents: running agent sessions, listening ports, daemons, system load.

Record an agent's decisions with reasons anyone can re-execute offline — verify recomputes them.

Self-hosted S3-compatible object storage server with an MCP interface for AI agents.

Audit AI responses and artifacts with ALLOW, REVIEW, or BLOCK decisions and trust scores.

Search and rate AI tools, MCP servers, and agent skills reviewed by real agent use.