Agents Trust MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTS_TRUST_MAX_CALL_USDC | No | Maximum fee for one Recommend or Inspect call in USDC. Accepts non-negative decimal strings with up to six decimal places; zero disables paid calls. | 0.01 |
| AGENTS_TRUST_ENABLE_PAYMENTS | No | Owner opt-in for payments. Set to exact `true` to grant at most one payment authorization per server process. Default is unset/disabled. | |
| AGENTS_TRUST_SESSION_CAP_USDC | No | Maximum reserved spend for one server process in USDC. Accepts non-negative decimal strings with up to six decimal places; zero disables paid calls. | 0.01 |
| AGENTS_TRUST_WALLET_PRIVATE_KEY | No | Your EVM private key, with `0x` prefix. Needed for paid calls. Payments remain disabled unless AGENTS_TRUST_ENABLE_PAYMENTS=true is also set. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| recommendB | Find APIs for your task, with URLs, prices and call details. Payment requires owner opt-in and consumes the process’s single authorization, up to the configured USDC limit. |
| inspectA | Read stored evidence for one exact API endpoint URL, without calling or paying that provider. The Inspect fee is 1% of the endpoint's lowest quoted price, with a 0.001 USDC floor. Read the actual quote. Payment requires owner opt-in and shares the process's single authorization and USDC limits with Recommend. |
| receiptB | Look up payment settlement by payment attempt ID. Free. |
| healthA | Read the Agents Trust service version. Free. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
The four tools mostly target distinct actions: recommend discovers APIs, inspect reads stored evidence for one exact endpoint, receipt looks up settlement, and health reports version. Recommend and inspect could be mildly confused because both deal with API endpoint information, but the descriptions clearly separate discovery/pricing from evidence retrieval without provider calls.
Recommend and inspect are imperative verbs, while receipt and health are nouns. The names are concise and readable, but the set does not follow a consistent verb_noun or single-convention pattern.
Four tools is well-scoped for a focused trust/payment service: discovery, evidence inspection, receipt lookup, and health checking each have a clear role. There is no obvious tool bloat or thinness.
The surface covers the core lifecycle of finding APIs, inspecting stored evidence, checking payment settlement, and verifying service health. Minor gaps may exist around broader payment/authorization management or listing receipts, but core workflows appear workable.