Example client code demonstrating integration with the ScrubMyText API for text scrubbing, action fingerprinting, approvals, signals, and retry-safe operations
This is an examples repository, not a functional MCP server. No MCP server implementation is present, only curl/shell/JavaScript/Python example scripts calling an external ScrubMyText API. Tools are inferred from documentation, not registered via MCP protocol. Schemas are partially visible in parameter descriptions but lack formal JSON Schema definitions. Descriptions are present but generic (10-50 chars). No error handling, no output schemas documented, no tool annotations. This cannot be deployed as an MCP server.
Check the status of an approval request
Mark an action as completed after execution
Create a signal (webhook inbox) for receiving events from external services
Generate a fingerprint for an action to derive a stable identity
Retrieve events from a signal inbox
Derive action identity and reserve it in one atomic operation
Request approval for an action with a title, description, and expiration time
Rework text using the ScrubMyText API in deep mode
No MCP server implementation present. Repository contains only example scripts (curl, Python, JavaScript) calling an external API. Tools are not registered via MCP protocol, they are inferred from documentation only.
No formal JSON Schema definitions for tool inputs. Parameter types and constraints are documented in text descriptions only, not in machine-parseable schema. LLMs cannot validate inputs against constraints.
No output schemas documented. Tools return JSON from external API but response structure is not specified. LLMs cannot plan downstream tool calls or extract required fields.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 25 | 2026-07-28+ | v2 |
Scrub text using the ScrubMyText API in standard mode
Tool descriptions are too brief (10-50 chars). Descriptions lack context on WHEN to use each tool, what it returns, and how it differs from similar tools. Example: 'Scrub text using the ScrubMyText API in standard mode' does not explain when to choose 'scrub' vs 'rework'.
No error handling or recovery guidance. Example scripts use bare urllib.urlopen() with no try/catch. If API returns 401, 404, or 500, the agent receives no actionable error message.