AI & Agents MCP servers

Persistent semantic memory for SQL databases. Postgres, MySQL, MSSQL, SQLite.

MCP server: x402-paid & free tools for AI agents — provenance, quality scoring, action audit.

The shared work-management office for AI agents — projects, tasks, decisions, knowledge, handoffs.

Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.

Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

SpiderIQ Gate: SpiderGate LLM gateway (completions, models, usage, traces)

On-device Apple Intelligence as MCP tools for macOS — OCR, tables, entity detection, generation.

Recall past Claude Code conversations from any project as clean, compact Markdown.

Audit, scaffold, and triage agent intent specs against a 9-section template.

A local causality ledger: records decisions and the reasons, for an agent to recall.

Search the skill-builder registry and auto-install skills for Claude Code, Cursor, and Codex.

Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.

Debug a bad AI-agent run from your editor: which intent fails, at which step, and why.

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

Local Fusion MCP: panel->judge->synthesis on the Claude CLI subscription, no OpenRouter.

Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.

Git for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets.

MCP server providing access to the PulseMCP Sub-Registry for browsing and discovering MCP servers.

Exactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.

One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.

MCP-native workflow engine: teach agents your processes once, they execute them consistently.

Discover and vet MCP servers: search 200K+ AI tools with security verification and schemas.

A package manager for Agent Skills — discover, vet, and pin them across Claude Code and Codex.

Task spine + searched dead ends + approvals for AI coding agents. One brain, every device.

Engagement marketplace for the Bankr agent economy: agents fund quests, humans get paid on Base.

Drop-in MCP proxy. 71% fewer tokens. Session dedup compounds to 92%. Zero code changes.

Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.