Verifiable, signed, immutable receipts for autonomous agent actions
Verifiable, signed, immutable receipts for autonomous agent actions
Persistent memory for AI agents, backed by cryptographic receipts. Every fact your agent learns is signed, traceable, and independently verifiable. No cloud required.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| track_action | Track an agent action with automatic hashing |
| create_receipt | Create a receipt with pre-computed hashes |
| complete_receipt | Complete a pending receipt with results |
| verify_receipt | Verify the cryptographic signature |
{
"mcpServers": {
"agent-receipts": {
"command": "npx",
"args": [
"@agent-receipts/mcp-server"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
A Model Context Protocol (MCP) server for Ragdoll AI knowledge base queries.
This app demonstrates use of MCP server and client in a local model chat via Ollama that incorporates web search via Serper.
A blazing-fast Model Context Protocol (MCP) Server built with FastMCP that seamlessly combines Neo4j's graph database capabilities with advanced vector search using embeddings. This server enables…
Semantic search over Nordic financial markets: filings, reports, and macro data for NO/SE/DK/FI.