Synpareia Trust Toolkit runs on your own machine — the client starts it, so there is no endpoint to ping. 199 installs a week from pypi. Last commit 7 Aug 2026.
Verifiable dealings with other agents: prove what you did, vet who you deal with, bind agreements
Today is the operative word: we check Synpareia Trust Toolkit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add trust-mcp -- uvx synpareia-trust-mcp
{
"mcpServers": {
"trust-mcp": {
"args": [
"synpareia-trust-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.trust-mcp]
command = "uvx"
args = ["synpareia-trust-mcp"]
{
"mcpServers": {
"trust-mcp": {
"args": [
"synpareia-trust-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"trust-mcp": {
"args": [
"synpareia-trust-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
SYNPAREIA_DATA_DIR (Where to store profile, recordings, and counterparty journal (default: ~/.synpareia)), SYNPAREIA_DISPLAY_NAME (Human-readable name for your agent), SYNPAREIA_NETWORK_URL (Synpareia network endpoint (default: the live network; set to 'none' for fully-local operation)), SYNPAREIA_WITNESS_URL (Witness service endpoint (default: the live witness; set to 'none' to disable)).
The author declared them in the registry entry; get the values from the project itself.
Find real, verifiable businesses with provenance and source URLs - for AI agents.
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
Ask "Are you on Trust Switch?" before your agent deals with another agent. Free. Never blocks.
Budget-capped x402 payments for AI agents: verifiable receipts, trust routing, 17 free tools.
Verifiable Earth ground truth for AI agents: water, hazard, ground stability, resource, with proof.
Tamper-evident record of what your AI agent did, plus local-first verifiable memory.
Deterministic GIS geoprocessing for AI agents, with verifiable provenance on every output
Discover, invoke, and trustlessly verify ForceDream AI agents with cryptographic proofs. 17 tools.
Answers built from our own checks of this server.