# online.sigmaintelligence/agentlab-services

> Signed-quality-receipt micro-services for agents; verify before you pay (x402/USDC).

- name: online.sigmaintelligence/agentlab-services
- version: 1.0.0
- connection class: unknown (unknown)
- trust: 53/100 flags: no-repository, unreachable
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/online.sigmaintelligence%2Fagentlab-services
- tools: https://api.protogrid.dev/v1/servers/online.sigmaintelligence%2Fagentlab-services/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agentlab-services": {
      "type": "http",
      "url": "https://sigmaintelligence.online/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 0
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website -unreachable(6 failures) +updated-21d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: productize_service (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); revenue_watch (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); market_brief (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 614 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 3 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 14, about 614 tokens to load them all
- tool set hash: 33872242cd43d94fcb4b4d3f6d5ead06
- tools last changed: 2026-09-30T22:35:22.815Z
- badge: [![protogrid quality](https://protogrid.dev/badge/online.sigmaintelligence/agentlab-services.svg)](https://protogrid.dev/servers/online.sigmaintelligence/agentlab-services)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-30 `revenue_watch` added
  - 30-day recurring revenue-leak monitor: reports newly appeared and resolved leaks against the last settled baseline, bound to a signed receipt.
- 2026-09-30 `revenue_leak` added
  - Revenue-leak diagnostic for an agent-economy seller: which discovery surfaces are missing and whether a buying agent can settle machine-to-machine at all.
- 2026-09-30 `trust_lease` added
  - 24-hour renewable trust passport for an agent/API: identity surfaces, schema availability and drift, bound to a signed receipt.

Full history: https://api.protogrid.dev/v1/servers/online.sigmaintelligence%2Fagentlab-services/changes

## Remotes

- https://sigmaintelligence.online/mcp (streamable-http, auth none, reachable false, uptime30d 0.7297297)

## Packages

_none_

## Tools (14)

- `attest_quality`: QA notary: independently quality-check ANOTHER agent's deliverable and issue a signed pass/fail.
- `audit_opportunity`: Conservative fit, fee, scam, eligibility and pay audit for a work opportunity.
- `clean_csv`: Clean, dedupe and normalize a CSV; returns a tidy CSV.
- `endpoint_safety`: Verify-before-you-pay: pre-flight scam/liveness/https screen of an x402 or MCP endpoint.
- `honesty_audit`: Honesty linter for AI output: flags unsupported certifications, fabricated authority and uncited statistics.
- `market_brief`: Evidence-backed demand/pain/opportunity brief for a topic (HN + StackExchange + GitHub signals).
- `notarize`: Proof-of-existence: signed, timestamped receipt binding any content to a hash (IP/plagiarism/audit).
- `productize_service`: Turn a raw capability into a fixed-scope, priced, machine-readable commercial offer.
- `rank_opportunities`: Rank candidate money/leads by euros-per-hour and speed-to-cash toward a target.
- `revenue_leak`: Revenue-leak diagnostic for an agent-economy seller: which discovery surfaces are missing and whether a buying agent can settle machine-to-machine at all.
- `revenue_watch`: 30-day recurring revenue-leak monitor: reports newly appeared and resolved leaks against the last settled baseline, bound to a signed receipt.
- `screen_message`: Phishing / social-engineering risk score for a message.
- `trust_lease`: 24-hour renewable trust passport for an agent/API: identity surfaces, schema availability and drift, bound to a signed receipt.
- `verify_text`: Deterministic quality check of a deliverable against a spec (length, coverage, honesty, structure).