MCP server wrapping the SigTAP Outreach API (x402 paid micro-tools, USDC on Base) as MCP tools. Supports stdio transport with automatic framing (Content-Length or line-delimited JSON). Free tools work with no wallet; paid tools proxy to live x402 API with payment settlement.
15 tools with complete input schemas and descriptions, but significant quality gaps. Tool names lack action verbs (catalog, score_preview, hash_preview are noun-heavy; only 3 of 15 start with clear verbs like 'decode'). Descriptions are brief (avg ~80 chars) and lack context on WHEN to use each tool or what happens on error. Parameters mostly typed but lack constraints (enums, ranges, patterns). No output schemas documented. No error handling guidance. email_grade and email_template lack 'required' arrays, leaving parameter optionality ambiguous. No tool annotations (readOnlyHint, destructiveHint). Pricing info in descriptions is helpful but not a substitute for proper parameter documentation.
List all SigTAP tools with prices and free previews. Free, no payment required.
Spot crypto price conversion (e.g. BTC/USD). $0.002/call.
SPF/DKIM/DMARC deliverability audit for a sending domain, with fixes. $0.003/call.
Domain age + registrar via RDAP - a proxy for prospect legitimacy. $0.003/call.
12-point cold email score with concrete fixes (subject + body). $0.005/call.
Personalized cold email from proven templates (persona, offer, name, company). $0.01/call.
Tool names lack action verbs. 'catalog', 'score_preview', 'hash_preview', 'json_tools' are noun-heavy or generic. LLMs infer intent from names, 'list_tools', 'grade_email_subject', 'hash_text_preview', 'validate_json' would be clearer.
No output schemas documented. LLMs cannot plan downstream calls or extract fields without knowing response structure. E.g., does email_grade return a score object, a list of fixes, or a string?
email_grade and email_template lack 'required' arrays in inputSchema. Parameter optionality is ambiguous, is 'body' required for email_grade? Are all email_template params required?
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | 2026-07-28+ | v2 |
FREE hash preview: SHA-256 and CRC32 of a string (truncated at 1000 chars).
SHA-256/384/512, hex, base64, base64url, CRC32 of a UTF-8 string. $0.001/call.
Validate / minify / pretty-print JSON. $0.001/call.
Decode a JWT (header/payload) with expiry and safety flags. No signature check. $0.001/call.
Test a regex against text with ReDoS safety check. $0.001/call.
FREE preview of the 12-point cold email grader: scores a subject line only.
URL-safe slug from text, optional max length. $0.001/call.
Batch-generate UUIDs (v4). $0.001/call.
Current weather by lat/lon (for geo-aware messaging). $0.001/call.
No error handling guidance. Descriptions do not explain what happens on failure (e.g., invalid domain, API timeout, payment required). LLMs cannot recover without explicit recovery hints.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are read-only, but this is not declared. Agents cannot distinguish safe tools from destructive ones.