# Blinka Machine Mouths

> Paid agent tools plus free procurement discovery and validation. No private Mika state exposed.

- name: io.github.tsukiryuu/blinka-machine-mouths
- version: 0.2.0
- connection class: unknown (unknown)
- trust: 69/100 flags: unreachable
- quality: 73/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.tsukiryuu%2Fblinka-machine-mouths
- tools: https://api.protogrid.dev/v1/servers/io.github.tsukiryuu%2Fblinka-machine-mouths/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "blinka-machine-mouths": {
      "type": "http",
      "url": "https://blinka-machine-mouths.netlify.app/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 7
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website -unreachable(3 failures) +updated-18d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 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: structure_json (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); code_signal_python (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); procurement_catalog (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,383 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 10 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: 10, about 1,383 tokens to load them all
- tool set hash: ec6dc66473f18cd713a89f5549b9fa95
- tools last changed: 2026-10-05T23:20:02.129Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.tsukiryuu/blinka-machine-mouths.svg)](https://protogrid.dev/servers/io.github.tsukiryuu/blinka-machine-mouths)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-05 `acceptance_check_delivery` added
  - Paid $1.00 Base USDC. Independently check a supplied delivery only against supplied acceptance criteria. Returns criterion-level pass/fail/unclear evidence. No browsing, tool execution, private Mika context, hidden-state inference, or retained input.
- 2026-10-02 `validate_procurement_request` added
  - Free public procurement preflight. Validate a buyer-authored authority-verification request against the public request schema and return a non-binding scope-review handoff with candidate bounded services. No request body is retained and no payment occurs.
- 2026-10-02 `procurement_catalog` added
  - Free public discovery. List Blinka/Little Life Moths bounded service offers plus the machine-readable procurement request schema and public submission channels. Does not accept work, take payment, or expose private Mika state.
- 2026-10-02 `rescue_workflow_pro` added
  - Paid $3.00 Base USDC. Premium failed-run repair packet: evidence-bound workflow recovery plus bounded Python code or text/config review, prioritized fixes, retry traps, and an exact tool-bounded next action. Artifacts are never executed.
- 2026-10-02 `code_review_python` added
  - Paid $0.25 Base USDC. Review caller-supplied Python source against its intended behavior for high-confidence bugs, security issues, missing edge cases, and repair suggestions. Code is parsed/reviewed but never executed or retained.
- 2026-10-02 `debug_python_error` added
  - Paid $0.01 Base USDC. Debug Python code from source plus an observed error/exception/traceback. Returns a bounded diagnosis, evidence, strongest static issue, and suggested fix. Submitted source is never executed or retained.
- 2026-10-02 `code_signal_python` added
  - Paid $0.005 Base USDC. Fast static Python bug/security preflight with an optional cost-transparent /code-review continuation only for high/critical or multiple findings. Code is parsed but never executed or retained.
- 2026-10-02 `rescue_signal` added
  - Paid $0.005 Base USDC. Cheap first-pass failed-run triage: evidence-backed blocker, retry trap, smallest next state change, and an optional smallest-sufficient continuation route when more help is warranted. No followup is purchased or executed automatically.
- 2026-10-02 `recover_workflow` changed (description)
  - before: Paid $0.25 Base USDC. Recover a failed/stalled run into completed state, blockers, retry traps, unknowns, and the smallest safe next action constrained to exact caller-supplied tool names.
  - after: Paid $0.25 Base USDC. Diagnose a failed workflow, deployment, or agent run into completed state, blockers, retry traps, unknowns, and the smallest safe next action constrained to exact caller-supplied tool names, plus a deterministic continuation contract with explicit authority non-inheritance. The service never executes the continuation.
- 2026-10-02 `structure_json` changed (description)
  - before: Paid $0.01 Base USDC. Convert unstructured text into a caller-supplied JSON Schema using only explicit source evidence. No URL fetch, private Mika state, or retained request body.
  - after: Paid $0.01 Base USDC. Extract JSON from unstructured text, prose, notes, or logs into a caller-supplied JSON Schema using only explicit source evidence. No URL fetch, private Mika state, or retained request body.

Full history: https://api.protogrid.dev/v1/servers/io.github.tsukiryuu%2Fblinka-machine-mouths/changes

## Remotes

- https://blinka-machine-mouths.netlify.app/mcp (streamable-http, auth none, reachable false, uptime30d 0.9230769)

## Packages

_none_

## Tools (10)

- `acceptance_check_delivery`: Paid $1.00 Base USDC. Independently check a supplied delivery only against supplied acceptance criteria. Returns criterion-level pass/fail/unclear evidence. No browsing, tool execution, private Mika context, hidden-state inference, or retained input.
- `code_review_python`: Paid $0.25 Base USDC. Review caller-supplied Python source against its intended behavior for high-confidence bugs, security issues, missing edge cases, and repair suggestions. Code is parsed/reviewed but never executed or retained.
- `code_signal_python`: Paid $0.005 Base USDC. Fast static Python bug/security preflight with an optional cost-transparent /code-review continuation only for high/critical or multiple findings. Code is parsed but never executed or retained.
- `debug_python_error`: Paid $0.01 Base USDC. Debug Python code from source plus an observed error/exception/traceback. Returns a bounded diagnosis, evidence, strongest static issue, and suggested fix. Submitted source is never executed or retained.
- `procurement_catalog`: Free public discovery. List Blinka/Little Life Moths bounded service offers plus the machine-readable procurement request schema and public submission channels. Does not accept work, take payment, or expose private Mika state.
- `recover_workflow`: Paid $0.25 Base USDC. Diagnose a failed workflow, deployment, or agent run into completed state, blockers, retry traps, unknowns, and the smallest safe next action constrained to exact caller-supplied tool names, plus a deterministic continuation contract with explicit authority non-inheritance. The service never executes the continuation.
- `rescue_signal`: Paid $0.005 Base USDC. Cheap first-pass failed-run triage: evidence-backed blocker, retry trap, smallest next state change, and an optional smallest-sufficient continuation route when more help is warranted. No followup is purchased or executed automatically.
- `rescue_workflow_pro`: Paid $3.00 Base USDC. Premium failed-run repair packet: evidence-bound workflow recovery plus bounded Python code or text/config review, prioritized fixes, retry traps, and an exact tool-bounded next action. Artifacts are never executed.
- `structure_json`: Paid $0.01 Base USDC. Extract JSON from unstructured text, prose, notes, or logs into a caller-supplied JSON Schema using only explicit source evidence. No URL fetch, private Mika state, or retained request body.
- `validate_procurement_request`: Free public procurement preflight. Validate a buyer-authored authority-verification request against the public request schema and return a non-binding scope-review handoff with candidate bounded services. No request body is retained and no payment occurs.