# Compass by 402rates (remote · api.402rates.com)

Free agent tests (no account or payment); paid ping.

- Trust score: 70/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-27

## Components

- remote · `api.402rates.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/com-402rates-compass/mcp-compass.md), [page](https://verifymcp.io/servers/com-402rates-compass/mcp-compass)

## Channel facts

- Endpoint: `https://api.402rates.com/mcp/compass`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-27.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1263 tokens (~114/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 38/100
  - Stability check failed: schema churn in the 17 days we've observed: 0 tool removals, 4 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Compass by 402rates MCP server?

Compass by 402rates is a hosted endpoint at https://api.402rates.com/mcp/compass, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-402rates-compass 'https://api.402rates.com/mcp/compass'
```

### Cursor

```json
{
  "mcpServers": {
    "com-402rates-compass": {
      "url": "https://api.402rates.com/mcp/compass"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-402rates-compass": {
      "type": "http",
      "url": "https://api.402rates.com/mcp/compass"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-402rates-compass]
url = "https://api.402rates.com/mcp/compass"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-402rates-compass": {
      "type": "remote",
      "url": "https://api.402rates.com/mcp/compass",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-402rates-compass --url 'https://api.402rates.com/mcp/compass' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-402rates-compass:
    url: "https://api.402rates.com/mcp/compass"
```

### Netclaw

```json
{
  "McpServers": {
    "com-402rates-compass": {
      "Transport": "http",
      "Url": "https://api.402rates.com/mcp/compass"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-402rates-compass -t streamable-http -u 'https://api.402rates.com/mcp/compass'
```

### Other

```json
{
  "mcpServers": {
    "com-402rates-compass": {
      "type": "http",
      "url": "https://api.402rates.com/mcp/compass"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-26 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 32 to 35.

### 2026-09-25 (score 69, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 69, −2)

- [security regression] Stability: 0.43 → fail
- [functional regression] “execute_test_action” made “access_token” required, so existing callers break
- [functional regression] “execute_test_action” made “action_key” required, so existing callers break
- [functional regression] “execute_test_action” made “run_id” required, so existing callers break
- [functional regression] “execute_test_action” made “task_id” required, so existing callers break
- [functional regression] “inspect_test_state” made “access_token” required, so existing callers break
- [functional regression] “inspect_test_state” made “run_id” required, so existing callers break
- [functional regression] “inspect_test_state” made “task_id” required, so existing callers break
- [functional regression] “read_agent_test_report” made “access_token” required, so existing callers break
- [functional regression] “read_agent_test_report” made “run_id” required, so existing callers break
- [functional regression] “start_agent_test” made “case_id” required, so existing callers break
- [functional] Server version: 0.2.0 → 0.2.1
- [cosmetic] “describe_agent_test” reworded the description of “case_version”
- [cosmetic] “start_agent_test” reworded the description of “case_version”

### 2026-09-23 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-21 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (11)

### `list_agent_test_cases` (~40 tokens)

List the synthetic agent test cases

Free catalogue of versioned synthetic cases: unavailable confirmation, retry credits and attempt limits, and partial results with continuation. No run, wallet or payment.

### `describe_agent_test` (~115 tokens)

Describe a synthetic agent test

Free 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.

Input parameters:

- `case_id` (string): Versioned synthetic case identifier.
- `case_version` (string): Optional exact case version. A new run defaults to the current published version; a linked repeat retains its previous version. The resolved version is returned and stored.
- `variant` (string): Budget case: budget_first or attempts_first. Linked repeats retain the previous variant.

### `start_agent_test` (~190 tokens)

Start or repeat a synthetic agent test

Create 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.

Input parameters:

- `access_token` (string): Secret short-lived run token. Omitted from reports. MCP client history may retain this argument.
- `case_id` (string, required): Versioned synthetic case identifier.
- `case_version` (string): Optional exact case version. A new run defaults to the current published version; a linked repeat retains its previous version. The resolved version is returned and stored.
- `configuration_changed` (boolean): Optional caller-declared change since the previous run; not independently verified.
- `previous_run_id` (string): Optional finalized run to repeat. Its access token authenticates this start.
- `variant` (string): Budget case: budget_first or attempts_first. Linked repeats retain the previous variant.

### `execute_test_action` (~201 tokens)

Execute a synthetic test action

Execute 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.

Input parameters:

- `access_token` (string, required): Secret short-lived run token. Omitted from reports. MCP client history may retain this argument.
- `action_key` (string, required): Caller-generated UUID. Identical key and payload identify the same synthetic operation.
- `action_type` (string): Case action: attempt, get_page or submit_result. Not accepted by the original case.
- `cursor` (string): Partial-result page cursor: first or second.
- `quantity` (integer): Synthetic quantity. The task specifies one unit.
- `record_ids` (array): Synthetic record identifiers submitted by the caller, at most six.
- `run_id` (string, required): Run identifier from start_agent_test.
- `task_id` (string, required): Task identifier bound to this run.

### `inspect_test_state` (~91 tokens)

Read synthetic task state

Read operation records for a synthetic task. Observation timestamps and state describe the test service only. No claim about client receipt or overall agent reliability.

Input parameters:

- `access_token` (string, required): Secret short-lived run token. Omitted from reports. MCP client history may retain this argument.
- `run_id` (string, required): Run identifier from start_agent_test.
- `task_id` (string, required): Task identifier bound to this run.

### `read_agent_test_report` (~109 tokens)

Read or finalize an agent test timeline

Read 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.

Input parameters:

- `access_token` (string, required): Secret short-lived run token. Omitted from reports. MCP client history may retain this argument.
- `finalize` (boolean): True freezes the run and prevents further actions. Omitted means read only.
- `run_id` (string, required): Run identifier from start_agent_test.

### `check_payment_terms` (~105 tokens)

Inspect x402 payment terms without making a payment

Free inspection of supplied x402 v1/v2 payment terms against the SDK schema and optional network, asset, recipient and atomic budget constraints. Exact EVM profile checks only. No wallet connection, external fetch, signature verification or settlement. Other profiles are explicitly untested.

Input parameters:

- `challenge` (object): Decoded PaymentRequired object from HTTP or MCP structuredContent. No signed payment or credentials.
- `expected` (object): Optional exact terms. An atomic budget requires network and asset.

### `list_capabilities` (~31 tokens)

List capabilities for Compass by 402rates

Free capability and MCP tool catalogue for Compass by 402rates. Contains this product and shared service information only.

### `find_x402_resource` (~223 tokens)

Find an x402 resource that can answer a question

Searches 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 two, and days since the last payment. Every figure is a count and carries its definition; no entry is scored, rated or labelled. Answers from a dated weekly snapshot and states which day it is from. Free.

Input parameters:

- `limit` (integer): how many results to return, 1 to 50 (default 10)
- `max_price` (number): highest price per call in USDC to include
- `network` (string): chain id a resource must accept payment on, for example eip155:8453
- `q` (string): words to look for in the provider's own description, service name, URL and tags. Every word must appear as a whole word; there is no stemming, so "yield" does not match "yields". Omit to list the res…

### `get_manifest` (~54 tokens)

Get the manifest for Compass by 402rates

Free OpenAPI manifest for Compass by 402rates. Contains this product and shared service information only.

Input parameters:

- `base_url` (string): absolute origin to render into the manifest's servers block. Defaults to the configured public base URL.

### `test_payment` (~104 tokens)

Payment integration check

Payment 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 networks for each transport. The receipt identifies the paid network and transaction. Business/professional use only. Terms: https://402rates.com/data-terms/ Price: 0.001 USDC per call over x402.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-402rates-compass/mcp-compass#diagnostics

## Score history

- 2026-09-27: 70
- 2026-09-26: 70
- 2026-09-25: 69
- 2026-09-24: 69
- 2026-09-23: 71
- 2026-09-22: 70
- 2026-09-21: 70
- 2026-09-20: 69
- 2026-09-19: 69
- 2026-09-18: 68
- 2026-09-17: 68
- 2026-09-16: 67
- 2026-09-15: 67
- 2026-09-14: 66
- 2026-09-13: 66
- 2026-09-12: 66
- 2026-09-11: 65
- 2026-09-10: 65

## Common questions

### What is the Compass by 402rates MCP server?

Compass by 402rates is an MCP server listed in the public MCP registry as com.402rates/compass. Free agent tests (no account or payment); paid ping. This page covers its hosted endpoint (https://api.402rates.com/mcp/compass).

### Is the Compass by 402rates MCP server safe to use?

Compass by 402rates scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Compass by 402rates MCP server expose?

Compass by 402rates exposes 11 tools: list_agent_test_cases, describe_agent_test, start_agent_test, execute_test_action, inspect_test_state, and 6 more. Their descriptions and schemas cost roughly 1,263 tokens of context every time the server is loaded.

### Does the Compass by 402rates MCP server require authentication?

No. We connected to Compass by 402rates without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Compass by 402rates MCP server still maintained?

Compass by 402rates is still listed as active in the MCP registry. We last reached this channel on 27 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.402rates.com/mcp/compass
- Website: https://402rates.com/compass/
- Changelog RSS feed: https://verifymcp.io/servers/com-402rates-compass/mcp-compass.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-402rates-compass/mcp-compass.json
- HTML version of this page: https://verifymcp.io/servers/com-402rates-compass/mcp-compass