
402rates MCP server
Which servers in the official MCP registry are 402rates's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-24
- Registry namecom.402rates/compassverified in the MCP registry
The registry name sits under 402rates.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools13
- Server calls itself402rates-compass
- Server version0.5.0
- Protocol version2025-06-18
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 473 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer487 ms
- Space in an agent's context≈ 3,240 tokensthe definitions of all its tools (13), which an agent carries on every turn
- Tool definitionsA · 99 of 100
- Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 1 of 13
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_agent_test_casesFree catalogue of versioned synthetic cases: unavailable confirmation, retry credits and attempt limits, and partial results with continuation. No run, wallet or payment.
describe_agent_testFree description of a versioned synthetic task, its limits and coverage. Optional case selection; omitted selection describes the original confirmation case. No run, payment or wallet.
start_agent_testCreate a free bounded synthetic run without an account. An optional finalized previous run and its token link a repeat of the same case version and scenario. No real purchase. Caller model costs remain external.
execute_test_actionExecute the selected case's action: synthetic order, retry attempt, page retrieval or result submission. Identical keys and input replay the stored outcome. Calls, effects and simulated credits remain observable. No real payment.
inspect_test_stateRead operation records for a synthetic task. Observation timestamps and state describe the test service only. No claim about client receipt or overall agent reliability.
read_agent_test_reportRead calls, timestamps, operations and resulting state. Optional finalization freezes the run. A linked repeat includes the previous frozen report while retained. No score, certification or judgment of the agent.
decode_payment_attributionFree local decoding of an ERC-8021 schema-2 x402 builder-code suffix from supplied calldata. Separates application, facilitator, services and facilitator-reported metadata. No transaction lookup, receipt confirmation, identity…
compare_payment_termsFree comparison of two unsigned captures for the same resource and method. Default analysis version 1 retains Exact EVM; version 2 compares documented Exact, Upto, Batch Settlement and Auth-Capture fields, limits and lifecycle terms…
check_payment_termsFree inspection of unsigned x402 terms. Default analysis version 1 retains Exact EVM checks; analysis_version 2 inspects documented EVM Exact, Upto, Batch Settlement and Auth-Capture profiles, declared limits and lifecycle fields. Unknown…
list_capabilitiesFree capability and MCP tool catalogue for Compass by 402rates. Contains this product and shared service information only.
find_x402_resourceSearches the x402 resource catalogue and returns matching paid endpoints with their price, the chains they accept, and their 30-day usage from the catalogue's own counters: total calls, distinct paying addresses, the ratio between the…
get_manifestFree OpenAPI manifest for Compass by 402rates. Contains this product and shared service information only.
test_paymentPayment integration check for 0.001 USDC; no external data lookup. Returns time, rail, network mode and free/paid capabilities. HTTP payment options can include Base, Polygon, Arbitrum and XDC; the challenge lists currently available…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"compass": {
"type": "http",
"url": "https://api.402rates.com/mcp/compass"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http 402rates https://api.402rates.com/mcp/compassclaude.ai, ChatGPT and other clients: add https://api.402rates.com/mcp/compass as a custom connector in the settings.
- com.402rates/ratesanswers, 13 toolsverified in the MCP registry
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.