AI & Agents MCP servers

Local-first, state-centric memory for coding agents. MCP server + CLI.

Does the tool do what it says? Conformance receipts for MCP servers, and unknown when unchecked.

Secure MCP access to Onyx search, chat, projects, and administration.

OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.

MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.

Tamper-evident records of AI agent decisions. Verify offline, or publish a proof link.

Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.

MCP stdio server for Attestify OS — governed agent execution and Attestify Trust signed evidence.

Your agent gets trustworthy tools on sites without WebMCP — data-only packages you approve.

MCP server giving AI agents persistent SQLite memory that proves which lessons hold.

A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown.

Drive terminal coding agents by voice, with receipts that never claim more than they proved.

Record agent judgments and their real outcomes on GRAFOMEM Cloud. Capture now, score later.

Verifiable receipts for governed process changes; emit, validate, and gate trust

LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.

Gating proxy for MCP servers: policy, verification and one audit trail across upstreams.

Route long-tail MCP servers through three lazy tools and reviewed declarative Methods.

Vantio Optics — read-only Sight Loop observe for agents. Proofs, hosts, upgrade path.

Durable user/project memory for MCP clients: recall context and remember selected facts.

Meta-MCP gateway: search, inspect and call any MCP server from the public registries.

Search agent skills ranked by measured lift vs a no-skill baseline, with safety and rankings.

Sealgate gateway proxy: list governed MCP servers and review agent session and audit status.

Pre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.

Search, build and manage Inflectiv datasets and AI agents, plus ChainAware on-chain intelligence.

Agent runtime with typed memory, knowledge and code graphs, plus file and web tools

Persistent memory and virtual filesystem MCP server for AI agents.

Offload grunt work from your premium agent to cheap models — auto-routing and billing isolation.

Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.