# SignalHarness.ai (remote · signalharness.ai)

330 production AI-agent services for data, validation, AI, crypto, and x402 pay-per-use.

- Trust score: 87/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `signalharness.ai`: 87/100 (this document), [markdown](https://verifymcp.io/servers/ai-signalharness-mcp/api-agent-services-mcp.md), [page](https://verifymcp.io/servers/ai-signalharness-mcp/api-agent-services-mcp)

## Channel facts

- Endpoint: `https://signalharness.ai/api/agent/services/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-10-17.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 83/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 397 tokens (~132/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 87/100
  - Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 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 SignalHarness.ai MCP server?

SignalHarness.ai is a hosted endpoint at https://signalharness.ai/api/agent/services/mcp, 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 ai-signalharness-mcp 'https://signalharness.ai/api/agent/services/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-signalharness-mcp": {
      "url": "https://signalharness.ai/api/agent/services/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-signalharness-mcp": {
      "type": "http",
      "url": "https://signalharness.ai/api/agent/services/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-signalharness-mcp]
url = "https://signalharness.ai/api/agent/services/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-signalharness-mcp": {
      "type": "remote",
      "url": "https://signalharness.ai/api/agent/services/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-signalharness-mcp --url 'https://signalharness.ai/api/agent/services/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-signalharness-mcp:
    url: "https://signalharness.ai/api/agent/services/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-signalharness-mcp": {
      "Transport": "http",
      "Url": "https://signalharness.ai/api/agent/services/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-signalharness-mcp -t streamable-http -u 'https://signalharness.ai/api/agent/services/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-signalharness-mcp": {
      "type": "http",
      "url": "https://signalharness.ai/api/agent/services/mcp"
    }
  }
}
```

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.

### 2026-10-16 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 84, +2)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 63. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-05 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-03 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-02 (score 80, +62)

- [security improvement] Authorization: unverified → partial
- [security improvement] HTTPS: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security improvement] HSTS header: fail → pass
- [security improvement] Transport: fail → pass
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.37

### 2026-10-01 (score 18, −61)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.30 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] HTTPS: pass → unverified
- [security regression] Transport: pass → fail
- [security regression] HSTS header: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

## MCP tools (3)

### `list_services` (~65 tokens)

List SignalHarness services

Discover the currently enabled public SignalHarness service catalog before choosing a service. This free, read-only call takes no arguments and returns a compact service array with canonical IDs, descriptions, prices, and supported payment metadata. Results follow the canonical catalog order; compare services by their exact service_id.

Output parameters:

- `error` (string): Stable machine error code when catalog discovery fails.
- `schemaVersion`: Catalog schema version when supplied by the runtime.
- `services` (array): Enabled public services in canonical catalog order. Each item includes its exact service ID and available discovery and payment fields.

### `get_service` (~93 tokens)

Get SignalHarness service

Inspect one enabled public SignalHarness service before invoking it. Use an exact service_id returned by list_services. This free, read-only call returns the canonical description, input and output schemas, price, endpoint, and supported payment metadata when available; an unknown or disabled ID returns a normalized not-found error.

Input parameters:

- `service_id` (string, required): Exact canonical service ID from list_services; matching is case-sensitive and aliases are not accepted.

Output parameters:

- `error` (string): Stable machine error code when the service cannot be returned.
- `input_schema` (object): JSON Schema the invoke_service input must satisfy.
- `output_schema` (object): JSON Schema describing the service-specific success result.
- `service_id` (string): Exact canonical service ID.

### `invoke_service` (~214 tokens)

Invoke SignalHarness service

Run exactly one enabled public SignalHarness service with caller-supplied input. Call get_service first and validate input against its input_schema. An unpaid call returns the canonical x402 V2 PAYMENT-REQUIRED challenge plus the equivalent x402 V1 JSON challenge; a client can then retry once with payment in params._meta["x402/payment"]. The server never retries automatically. A paid call may settle the advertised charge and perform external work, then returns service-specific structured JSON or a normalized error.

Input parameters:

- `idempotency_key` (string): Optional stable key for retrying the same logical job safely. Reuse it only for recovery of that same job and payment.
- `input` (object, required): Caller-supplied job data. It must satisfy the selected service input_schema returned by get_service.
- `request_id` (string): Optional caller-generated request identifier for tracing this attempt. Never place secrets or payment credentials in it.
- `service_id` (string, required): Exact canonical ID of an enabled public service, obtained from list_services.

Output parameters:

- `error` (string): Stable machine error code for unpaid, invalid, failed, or unavailable requests.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-signalharness-mcp/api-agent-services-mcp#diagnostics

## Score history

- 2026-10-17: 87
- 2026-10-16: 87
- 2026-10-15: 86
- 2026-10-14: 86
- 2026-10-13: 85
- 2026-10-12: 85
- 2026-10-11: 84
- 2026-10-10: 84
- 2026-10-07: 82
- 2026-10-05: 82
- 2026-10-04: 81
- 2026-10-03: 81
- 2026-10-02: 80
- 2026-10-01: 18
- 2026-09-30: 79
- 2026-09-29: 79
- 2026-09-28: 78
- 2026-09-27: 78
- 2026-09-26: 77
- 2026-09-25: 77
- 2026-09-24: 76
- 2026-09-23: 76
- 2026-09-22: 75
- 2026-09-21: 63

## Common questions

### What is the SignalHarness.ai MCP server?

SignalHarness.ai is an MCP server listed in the public MCP registry as ai.signalharness/mcp. 330 production AI-agent services for data, validation, AI, crypto, and x402 pay-per-use. This page covers its hosted endpoint (https://signalharness.ai/api/agent/services/mcp).

### Is the SignalHarness.ai MCP server safe to use?

SignalHarness.ai scores 87 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 SignalHarness.ai MCP server expose?

SignalHarness.ai exposes 3 tools: list_services, get_service, invoke_service. Their descriptions and schemas cost roughly 372 tokens of context every time the server is loaded.

### Does the SignalHarness.ai MCP server require authentication?

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

### Is the SignalHarness.ai MCP server still maintained?

SignalHarness.ai is still listed as active in the MCP registry. We last reached this channel on 17 October 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://signalharness.ai/api/agent/services/mcp
- Website: https://signalharness.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-signalharness-mcp/api-agent-services-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-signalharness-mcp/api-agent-services-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-signalharness-mcp/api-agent-services-mcp