
Fidacy
com.fidacyPublished by fidacy.comv0.2.7Updated Oct 24, 2026
Payment firewall for AI agents: a signed, verifiable verdict on every money-moving action.
Overview
Local MCP server that gates AI agent payment actions against a signed mandate, returning allow/deny verdicts, short-lived grants and audit proofs.
- What you can do
- Request and authorize payments against a signed mandate, returning an allow with a short-lived Ed25519 grant or a deny with the violated rule
- Read the mandate envelope and the Fidacy public key used for verification
- Retrieve a hash-chained audit proof for a given decision id
- Request a signed trust verdict from the Fidacy engine for a proposed action such as a payment, message, voice call or document claim
- When to use it
- Use it when an agent can move money and you want a deterministic, verifiable gate in front of the executor instead of prompt-level guardrails, so wrong payees, inflated amounts or duplicate invoices are blocked before funds move.
- Requirements
- Runs locally over stdio via npx or a global npm install (Node.js). Works offline with a local config file listing trusted payees and caps. The optional assess_action verdict needs FIDACY_ENGINE_API_KEY with assess:write scope; production core wiring needs FIDACY_MODE=http and three HTTP endpoints.
Installation
In SourceWeft
- Open Fidacy in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
@fidacy/mcp
[Fidacy blocks a BEC lookalike-payee payment, then allows the legit one with a signed Ed25519 grant]
The action firewall for AI agents. A drop-in MCP server that gates payment actions against a cryptographically signed mandate before money can move. Non-custodial: Fidacy authorizes and proves, it never holds funds.
Install once, works in any MCP-compatible agent: Claude Code, Claude Desktop, Hermes, OpenClaw, and anything else that speaks MCP.
[npm] [license] Works with: Claude Code · Claude Desktop · OpenClaw · Hermes · Brex CrabTrap
Your agent could be paying scammers right now. Prompt-injected into the wrong payee, an inflated amount, or the same invoice twice — and your logs aren't evidence. Fidacy blocks it before money moves, and hands back a signed verdict anyone can verify against public keys. You don't trust us — you check the signature.
Quick start (free, local-first, no account)
Runs on your machine, offline, deny-by-default. Add trusted payees + caps in
~/.fidacy/config.json. Verify any verdict yourself against the public keys at
/.well-known/jwks.json.
Why
An agent can hallucinate or be prompt-injected into a payment: wrong payee,
wrong amount, fabricated invoice. Prompt-level guardrails are probabilistic and
bypassable. @fidacy/mcp is a deterministic gate between the agent's intent and
the executor: the action is dead on arrival unless it validates against a signed
mandate, and every decision lands in an immutable hash-chained audit trail.
Enforcement model
- Register
@fidacy/mcpas the agent's only payment-capable tool. Do not give the agent a raw payment tool. Tool inventory is the runtime firewall. - The agent calls
request_payment. Fidacy checks it against the mandate (payee allowlist, per-tx cap, total cap, currency, time window, revocation). - ALLOW returns a short-lived Ed25519 grant. DENY returns no grant and the violated rule. The downstream executor MUST require the grant, so a denied action cannot proceed.
- Every decision is appended to a hash-chained log.
get_audit_proofreturns the portable, verifiable proof.
One install, two backends
@fidacy/mcp ships two complementary capabilities in a single install:
- Verdict layer (advisory):
assess_actioncalls the live Fidacy engine and returns a signed trust verdict. It moves no money; it returns a judgment whose proof (riskPayloadJws+signingKeyId) is verifiable by anyone via@fidacy/verifyagainst the engine JWKS at/.well-known/jwks.json. - Payment firewall (enforcement):
request_payment/verify_mandate/get_audit_proofgate and prove a payment against a signed mandate through the core, returning short-lived Ed25519 grants.
Mental model: assess_action -> engine (signed verdict);
request_payment and friends -> core (payment firewall).
Tools
assess_action
Returns a signed Fidacy trust verdict from the live engine for a proposed
action. The signed proof is riskPayloadJws + signingKeyId, verifiable by
anyone via @fidacy/verify against {engineUrl}/.well-known/jwks.json.
Inputs:
kind(optional, defaultap2_payment): one ofap2_payment,message_send,voice_call,custom,claim_document.mandate(required): the action/mandate object for thatkind.mandateType,spendingMandate,idempotencyKey,a2a.task_id(optional).
Environment:
The server boots without FIDACY_ENGINE_API_KEY; the tool is always registered.
Only calling assess_action without the key returns a helpful error telling
you to set it. The key is never logged, echoed, or attached to any error.
Install
Claude Code
Claude Desktop (claude_desktop_config.json)
Hermes (config.yaml)
OpenClaw
Add the same server via the Tools panel, or the mcpServers block in your
agent config. Any MCP-compatible host uses the same command.
Wiring the real core (production)
The MCP layer talks to your core through one interface (FidacyCore). Your
repository stays private. Set FIDACY_MODE=http and implement three endpoints:
POST /v1/mandate/get->MandatePOST /v1/decide->Decision(runs your Ed25519/AP2 verification + audit append)POST /v1/audit/proof->AuditProof
No change to the MCP layer is needed.
Dev
Source: README.md at commit ce42c70
Tools
0Version history
1- v0.2.7LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts