Tinplate Edge AI Safety, Security & EU Compliance
Server Details
Stateless, zero-log Streamable HTTP MCP server exposing 42 deterministic tools for AI prompt-injection defense, PII redaction, secret scanning, MCP manifest linting, JSON repair, SSRF firewalling, and EU VAT/IBAN/Peppol validation.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 39 tools
Most tools target a recognizably distinct check, but there are several near-neighbor pairs: email_dns vs email_dns_generator, pii_redactor vs secret_scanner, prompt_guard vs llm_messages_guard vs llm_output_guard, and command_sql_guard vs agent_code_guard vs ssrf_firewall. The descriptions do draw the boundaries (audit vs generate, mask PII vs mask secrets, input vs output), so an agent can usually pick correctly, but selection requires reading carefully rather than relying on names. The split-tool variants (_verify, _restore, _vat, _add, _is_workday) are distinct endpoints of the same capability and are easy to confuse with their base tool.
All 39 tools share a uniform `tinplate_` prefix plus snake_case resource names, and variants follow a consistent suffix pattern (_verify, _restore, _vat, _add, _is_workday). The convention is noun-based rather than verb_noun, and names are long (e.g. tinplate_workday_holiday_is_workday), but it is predictable and readable. Minor deviation only in that sub-operations are expressed as suffixes rather than separate verbs.
39 tools is well beyond a scoped surface; the server bundles many unrelated one-off utilities (cron explainer, IBAN checksums, ICS sanitizer, SemVer diff, User-Agent parser) alongside AI-safety checks. The result is a flat catalog that forces the agent to scan a very long list to find the relevant validator. Splitting single APIs into 2-3 variant tools (e.g. workday_holiday has three) inflates the count further.
Individual capabilities are often covered in round trips (issue+verify receipts, issue+verify consent tokens, redact+restore PII/secrets), which is good. However the stated domain — AI safety, security, and EU compliance — is enormous and coverage is arbitrary: there is no EU AI Act risk classification, no compliance report/attestation generation, no SBOM or dependency-vulnerability lookup, and no way to list or retrieve previously issued receipts/tokens. Agents hitting those needs will dead-end.
Available Tools
39 toolstinplate_agent_action_receiptsBRead-onlyIdempotentInspect
Agent Action Receipts API: Issue and verify tamper-evident signed audit receipts for AI agent actions (integrity proof only). (Endpoint: POST /v1/agent-action-receipts/issue)
Inputs: agent_id (required), tool_name (required), kid, secret, +8 more.
tinplate_agent_action_receipts_verifyBRead-onlyIdempotentInspect
Agent Action Receipts API (verify): Issue and verify tamper-evident signed audit receipts for AI agent actions (integrity proof only). (Endpoint: POST /v1/agent-action-receipts/verify)
Inputs: jwks, keys, chain, secret, +4 more.
tinplate_agent_code_guardBRead-onlyIdempotentInspect
AI-Generated Code & CI Workflow Sandbox Auditor API: Audit LLM-generated Python, JS/TS, Shell, or GitHub Actions code for sandbox escapes before execution. (Endpoint: POST /v1/agent-code-guard)
Inputs: code (required), language, allow_network, allow_filesystem_write.
tinplate_command_sql_guardBRead-onlyIdempotentInspect
Agent Shell Command & SQL Query Safety Guard API: Flag risky agent shell commands and Text-to-SQL queries for RCE, reverse shells, and destructive SQL. (Endpoint: POST /v1/command-sql-guard)
Inputs: input (required), mode, sql_policy, allow_chaining, +2 more.
tinplate_consent_tokensCRead-onlyIdempotentInspect
Stateless Consent & One-Click Unsubscribe Tokens API: Issue and verify stateless HMAC unsubscribe tokens and RFC 8058 List-Unsubscribe headers. (Endpoint: POST /v1/consent-tokens/issue)
Inputs: scope (required), subject (required), kid, secret, +3 more.
tinplate_consent_tokens_verifyCRead-onlyIdempotentInspect
Stateless Consent & One-Click Unsubscribe Tokens API (verify): Issue and verify stateless HMAC unsubscribe tokens and RFC 8058 List-Unsubscribe headers. (Endpoint: POST /v1/consent-tokens/verify)
Inputs: token (required), keys, secret, now_epoch, +1 more.
tinplate_content_provenanceBRead-onlyIdempotentInspect
Content Metadata & C2PA Marker Inspector API: Inspect C2PA box markers and EXIF/XMP metadata tags (heuristic header signals, not authenticity proof). (Endpoint: POST /v1/content-provenance)
Inputs: metadata_text, content_base64.
tinplate_cron_explainerARead-onlyIdempotentInspect
Cron & Schedule Explainer & Validator API: Validate cron expressions, translate to plain English, and compute next N runs with DST. (Endpoint: POST /v1/cron-explainer)
Inputs: expression (required), count, timezone, from_time.
tinplate_email_dnsBRead-onlyIdempotentInspect
Email DNS Deliverability Auditor API: Audit MX, SPF 10-lookup limits, DMARC, DKIM, and MTA-STS with a 0–100 score. (Endpoint: POST /v1/email-dns)
Inputs: domain (required), records, dkim_selectors.
tinplate_email_dns_generatorBRead-onlyIdempotentInspect
SPF, DKIM & DMARC Record Linter & Generator API: Lint existing SPF/DMARC strings and generate clean, RFC-formatted DNS TXT records. (Endpoint: POST /v1/email-dns-generator)
Inputs: domain (required), ip4, ip6, aspf, +13 more.
tinplate_eu_vat_ibanCRead-onlyIdempotentInspect
EU VAT & IBAN/BIC Checksum Validator API: Validate IBAN MOD-97 checksums, BIC/SWIFT codes, and EU27 VAT formats offline. (Endpoint: POST /v1/eu-vat-iban/iban)
Inputs: iban (required), bic.
tinplate_eu_vat_iban_vatBRead-onlyIdempotentInspect
EU VAT & IBAN/BIC Checksum Validator API (vat): Validate IBAN MOD-97 checksums, BIC/SWIFT codes, and EU27 VAT formats offline. (Endpoint: POST /v1/eu-vat-iban/vat)
Inputs: vat_number (required), verify_vies.
tinplate_hallucination_diffBRead-onlyIdempotentInspect
Deterministic Hallucination Diff API: Fast first filter to catch unsupported numbers, dates, and names in LLM answers vs RAG sources. (Endpoint: POST /v1/hallucination-diff)
Inputs: answer (required), sources (required), strictness, use_ai_judge.
tinplate_hu_business_validatorARead-onlyIdempotentInspect
Hungarian Business ID & GIRO Checksum Validator API: Validate Hungarian adószám, adóazonosító jel, cégjegyzékszám, and GIRO bank accounts offline (checksum/format only). (Endpoint: POST /v1/hu-business-validator)
Inputs: adoszam, bank_account, cegjegyzekszam, adoazonosito_jel.
tinplate_ics_sanitizerBRead-onlyIdempotentInspect
ICS / iCalendar Feed Sanitizer & Validator API: Repair broken .ics calendar feeds, normalize Windows timezones to IANA, and parse VEVENTs. (Endpoint: POST /v1/ics-sanitizer)
Inputs: ics (required), fix_inverted_dates, normalize_windows_timezones.
tinplate_json_healBRead-onlyIdempotentInspect
Broken JSON & LLM Output Healer API: Repair malformed or truncated LLM JSON outputs into valid, schema-checked JSON in 1 ms. (Endpoint: POST /v1/json-heal)
Inputs: raw (required), schema.
tinplate_jwt_jwk_inspectorBRead-onlyIdempotentInspect
JWT, JWS & JWK Security Auditor & RFC 8725 Linter API: Audit JWT tokens and JWK sets against RFC 8725 for alg:none, weak secrets, and leaked keys. (Endpoint: POST /v1/jwt-jwk-inspector)
Inputs: jwk, token, hmac_secret, max_ttl_seconds, +1 more.
tinplate_llm_messages_guardBRead-onlyIdempotentInspect
LLM Chat Messages Policy Proxy & Sanitizer API: Sanitize entire multi-turn LLM messages[] arrays in one call before forwarding to OpenAI, Anthropic, or Gemini. (Endpoint: POST /v1/llm-messages-guard)
Inputs: messages (required), locales, redact_pii, sensitivity, +3 more.
tinplate_llm_output_guardBRead-onlyIdempotentInspect
LLM Output Safety, Leakage & Format Guardrail API: Scan and sanitize LLM outputs for prompt leakage, Markdown beacons, XSS, and policy violations. (Endpoint: POST /v1/llm-output-guard)
Inputs: output (required), blocked_terms, canary_tokens, system_prompt, +2 more.
tinplate_locale_value_parserBRead-onlyIdempotentInspect
Text-to-Structured Date, Money & Unit Parser API: Normalize messy EU/US prices, dates, percentages, and measurements into structured JSON. (Endpoint: POST /v1/locale-value-parser)
Inputs: text (required), locale_hint, reference_time.
tinplate_mcp_manifest_linterBRead-onlyIdempotentInspect
MCP Server Manifest & Tool Security Linter API: Audit MCP server manifests for hidden tool poisoning, shell risks, and excessive permissions. (Endpoint: POST /v1/mcp-manifest-linter)
Inputs: manifest (required), strict_schemas.
tinplate_pii_redactorARead-onlyIdempotentInspect
PII Redactor API: Mask emails, phones, IBANs, cards, IPs, SSNs, EU VATs, and HU IDs with reversible tokens before LLM calls. (Endpoint: POST /v1/pii-redactor)
Inputs: text (required), mode, types, locales.
tinplate_pii_redactor_restoreCRead-onlyIdempotentInspect
PII Redactor API (restore): Mask emails, phones, IBANs, cards, IPs, SSNs, EU VATs, and HU IDs with reversible tokens before LLM calls. (Endpoint: POST /v1/pii-redactor/restore)
Inputs: tokens (required), redacted_text (required).
tinplate_prompt_cache_budgeterBRead-onlyIdempotentInspect
Prompt Cache Key & Context Budgeter API: Estimate tokens, optimize message order for prompt caching, and calculate LLM API costs. (Endpoint: POST /v1/prompt-cache-budgeter)
Inputs: blocks (required), model, max_context_tokens, estimated_cache_hits, +1 more.
tinplate_prompt_guardBRead-onlyIdempotentInspect
Prompt Injection Detection API: Catch prompt injections, role hijacks, and encoded jailbreaks in user inputs and RAG chunks. (Endpoint: POST /v1/prompt-guard)
Inputs: text (required), context, sensitivity, use_ai_judge, +1 more.
tinplate_rag_chunkerBRead-onlyIdempotentInspect
Markdown & Code Aware Smart RAG Document Chunker API: Split Markdown into token-budgeted RAG chunks with heading breadcrumbs and intact code/tables. (Endpoint: POST /v1/rag-chunker)
Inputs: text (required), max_tokens, overlap_tokens, prepend_breadcrumbs, +1 more.
tinplate_regex_safetyARead-onlyIdempotentInspect
Regex ReDoS Vulnerability Scanner & Pattern Explainer API: Audit regular expressions for O(2^n) ReDoS backtracking, explain patterns, and test matches. (Endpoint: POST /v1/regex-safety)
Inputs: pattern (required), flags, test_strings.
tinplate_schema_diffBRead-onlyIdempotentInspect
OpenAPI & JSON Schema Breaking-Change Diff API: Diff two OpenAPI 3.x or JSON Schemas to flag breaking and non-breaking contract changes. (Endpoint: POST /v1/schema-diff)
Inputs: after (required), before (required), mode.
tinplate_secret_scannerBRead-onlyIdempotentInspect
Log Redact & Secret Scanner API: Detect and mask leaked API keys, JWTs, and private keys in logs, diffs, and prompts. (Endpoint: POST /v1/secret-scanner)
Inputs: text (required), mode, types, min_entropy, +1 more.
tinplate_secret_scanner_restoreCRead-onlyIdempotentInspect
Log Redact & Secret Scanner API (restore): Detect and mask leaked API keys, JWTs, and private keys in logs, diffs, and prompts. (Endpoint: POST /v1/secret-scanner/restore)
Inputs: tokens (required), redacted_text (required).
tinplate_semver_lockfile_judgeARead-onlyIdempotentInspect
SemVer & Package Manifest / Lockfile Diff Judge API: Diff two package.json files to flag breaking SemVer bumps and risky dependency changes. (Endpoint: POST /v1/semver-lockfile-judge)
Inputs: after (required), before (required), fail_on_zero_ver_minor, include_dev_dependencies.
tinplate_ssrf_firewallARead-onlyIdempotentInspect
Agent URL & SSRF Signal Validator API: Flag untrusted URLs and redirect chains for SSRF signals (advisory pre-check, not a sandbox). (Endpoint: POST /v1/ssrf-firewall)
Inputs: url (required), check_dns, inspect_redirects.
tinplate_tabular_rag_cleanerBRead-onlyIdempotentInspect
Tabular CSV/JSON RAG Sanitizer & Formula-Injection Guard API: Neutralize CSV formula injection, redact cell-level PII, and convert tables into RAG-ready Markdown & row chunks. (Endpoint: POST /v1/tabular-rag-cleaner)
Inputs: csv, rows, delimiter, redact_pii, +3 more.
tinplate_tool_call_validatorBRead-onlyIdempotentInspect
Agent Tool-Call Validator & Repairer API: Validate and auto-repair broken LLM tool-call arguments against your JSON Schema. (Endpoint: POST /v1/tool-call-validator)
Inputs: tools (required), tool_call (required), coerce_types, apply_defaults, +2 more.
tinplate_ua_bot_parserBRead-onlyIdempotentInspect
User-Agent & AI Bot Parser API: Detect AI training crawlers, RAG bots, headless browsers, and device/OS details from User-Agent. (Endpoint: POST /v1/ua-bot-parser)
Inputs: user_agent (required).
tinplate_url_normalizerBRead-onlyIdempotentInspect
URL Normalizer & Tracking Parameter Stripper API: Canonicalize URLs and strip 40+ ad-tracking params and utm_*/mtm_* prefixes for clean deduplication. (Endpoint: POST /v1/url-normalizer)
Inputs: url (required), strip_www, sort_query, force_https, +6 more.
tinplate_workday_holidayBRead-onlyIdempotentInspect
Workday & Holiday Calculator API: Calculate business days and SLA deadlines across 13 countries including HU swap Saturdays. (Endpoint: POST /v1/workday-holiday/between)
Inputs: country (required), end_date (required), start_date (required), include_end, +1 more.
tinplate_workday_holiday_addARead-onlyIdempotentInspect
Workday & Holiday Calculator API (add): Calculate business days and SLA deadlines across 13 countries including HU swap Saturdays. (Endpoint: POST /v1/workday-holiday/add)
Inputs: date (required), days (required), country (required).
tinplate_workday_holiday_is_workdayCRead-onlyIdempotentInspect
Workday & Holiday Calculator API (is-workday): Calculate business days and SLA deadlines across 13 countries including HU swap Saturdays. (Endpoint: POST /v1/workday-holiday/is-workday)
Inputs: date (required), country (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm37 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.