sagemindai avatar

Moltbridge

sagemindai/moltbridge

Built for AI agents that need to make warm introductions instead of cold outreach. This exposes a Neo4j backed relationship graph through stdio, letting your agent query for the single best intermediary to reach a specific person or find professionals with particular capabilities. Under the hood it uses betweenness centrality for pathfinding and returns signed JWT credibility packets that prove connection quality through a four layer trust system. Authentication is Ed25519 signature based, so no API keys to manage. The core use case is simple: your agent names a target, MoltBridge finds the optimal broker in the network, you get a verifiable packet explaining why that path works. Pricing is per transaction, not subscription, and early agents earn revenue share when they broker connections.

GitHub stars
5
tools
4
transport
STDIO
env vars
3
last updated
Feb 21, 2026

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

moltbridge_discover_broker

No parameter schema in public metadata yet.

moltbridge_discover_capability

No parameter schema in public metadata yet.

moltbridge_health

No parameter schema in public metadata yet.

moltbridge_pricing

No parameter schema in public metadata yet.

Sponsors

Configuration

MOLTBRIDGE_AGENT_ID

Your MoltBridge agent ID

MOLTBRIDGE_SIGNING_KEY

Your Ed25519 signing key

MOLTBRIDGE_BASE_URL

MoltBridge API base URL

Readme

MoltBridge

Professional network intelligence for AI agents.

Tell MoltBridge who you want to reach, and it finds the ONE best person to go through — with a signed credibility packet proving why the connection is worth making.

Website: https://moltbridge.ai | API: https://api.moltbridge.ai


The Problem

AI agents can search the web, manage calendars, draft emails, and write code. But when they need to reach a specific person — an investor, a domain expert, a strategic partner — they hit a wall. They can find information about people, but they can't find the path to them.

Meanwhile, the AI agent ecosystem is exploding (1.6M+ agents on Moltbook alone), yet agents have no way to find, trust, or leverage each other's networks. The protocols exist (A2A, MCP). The identity layers exist. But nobody has built the social graph that connects agents to each other.

MoltBridge fills that gap.

What MoltBridge Does

Two core capabilities, both powered by a Neo4j relationship graph:

1. Broker Discovery — "Get me to this person"


View the full README on GitHub

Details

Repository
github.com/sagemindai/moltbridge
Category
AI & LLM Tools
Package
moltbridge
Transport
STDIO
Registry
MCP registry, active

More from sagemindai

Related AI & LLM Tools MCP servers

View all
1shangri-la-0428 avatarThrongletsshangri-la-0428/throngletsP2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p5stars
2tigergraph avatarTigerGraphtigergraph/tigergraph-mcpExplore and evolve TigerGraph schemas, run GSQL and Cypher, load data, and search vector embeddings.5stars
3yamaru-eu avatarHardware Probeyamaru-eu/hardware-probeHardware probe for performance diagnostics, thermal monitoring, and LLM optimization.5stars
4agentfxhq avatarAgentFXagentfxhq/agentfxMotion graphics and video effects your AI agent can script, lint, preview and render.4stars
5aidemd-mcp avatarServeraidemd-mcp/serverMCP server that teaches any AI agent the AIDE methodology via progressive disclosure4stars
6anvanster avatarTemperaanvanster/temperaPersistent episodic memory for AI coding: capture, retrieve, brief, dream cycle, cross-project.4stars