TrustBoost PII Sanitizer

TrustBoost PII Sanitizer is a pay-per-call "privacy firewall" for autonomous AI agent pipelines, built and operated by an individual developer (Teodoro Crispin, GitHub teodorofodocrispin-cmyk) and served entirely from https://api.trustboost.dev — the apex trustboost.dev has no DNS record. An agent POSTs text to /sanitize and gets it back with emails, phone numbers, national IDs (RFC, CUIT, CPF, CNPJ, Personalausweis, マイナンバー, NIR, Codice Fiscale, RRN and more across 8 languages), API keys and financial data replaced by [REDACTED], plus a safety_score, a risk_category and an entity list; five context modes (general, legal, financial, medical, code) tune the redaction. There is no account and no API key: 50 free calls per wallet with tx_hash=TRIAL, a free 3-per-hour preview, then x402 payment in USDC on Base or Solana ($0.01 per call or a 149 USDC prepaid bundle of 10,000), with every paid sanitization anchored on Solana as a verifiable "Proof of Sanitization". The same service is exposed three ways from one host: a 9-operation OpenAPI 3.0.0 REST contract, a remote MCP server at /mcp (one tool, sanitize_pii), and an A2A-flavored agent card at /.well-known/agent-card.json with three skills. The provider's own privacy policy describes it as a learning prototype that sends raw text to OpenAI GPT-4o-mini for detection and has no certified security audit.

TrustBoost PII Sanitizer publishes 9 API contracts indexed on the APIs.io network, including Budget API, Health API, MCP API, and 6 more. Tagged areas include Privacy, PII Redaction, Data Protection, LLM Security, and AI Safety.

TrustBoost PII Sanitizer’s developer surface includes documentation, getting-started guide, API reference, pricing, support, sandbox, authentication, and 24 more developer resources.

🌐 Visit website 📡 Source on GitHub
50.1/100 developing ▬ flat Agent 30/100 agent ready Front door AI 5/6 prominent Full breakdown ↓
scored 2026-10-09 · rubric v0.23.0
2 published contracts 1 MCP Servers
PrivacyPII RedactionData ProtectionLLM SecurityAI SafetyAgentsA2AMCPx402Agentic CommerceSolanaComplianceAgent-Native

What this lets a business do 1

Business capabilities this provider's published APIs can perform, derived from its own contracts. Browse all capabilities →

Compliance Management
BC-130
Sanitize
POST /sanitize

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-10-09 · rubric v0.23.0
Composite quality — 50.1/100 · developing
Contract Quality 7.8 / 19
Developer Ergonomics 8.9 / 15
Access Clarity 9.5 / 15
Operational Transparency 2.3 / 10
Contract Governance 1.6 / 9
Discoverability 5.6 / 8
Regulatory Posture 5.4 / 15
Create-or-Update Ergonomics 0.0 / 10
Agent readiness — 30/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 10
Documented Reversibility 0 / 6
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 7 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 8 / 8
Dry-Run / Simulate Mode 0 / 4
Delegated User Identity 0 / 6
Protected Resource Metadata 0 / 5
Registration Without a Human 0 / 6
Agentic Commerce Well-Known Document 0 / 5
Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.
Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.
The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/trustboost-dev: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Standards implemented 1

Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.

x402
tagged — the provider's own APIs.json carries the standard as a tag; implementation not verified

APIs 9

Individual APIs this provider publishes, each with its own machine-readable definition.

TrustBoost MCP Server

Remote Model Context Protocol server at https://api.trustboost.dev/mcp (HTTP JSON-RPC 2.0, protocol version 2024-11-05, serverInfo trustboost 2.6.0). initialize and tools/list a...

TrustBoost A2A Agent

Agent2Agent surface: an agent card served from https://api.trustboost.dev/.well-known/agent-card.json (version 2.6.0, no protocolVersion, capabilities object of product flags, t...

TrustBoost PII Sanitizer Budget API

The Budget API from TrustBoost PII Sanitizer — 1 operation(s) for budget.

TrustBoost PII Sanitizer Health API

The Health API from TrustBoost PII Sanitizer — 1 operation(s) for health.

TrustBoost PII Sanitizer MCP API

The Mcp API from TrustBoost PII Sanitizer — 1 operation(s) for mcp.

TrustBoost PII Sanitizer Message API

The Message API from TrustBoost PII Sanitizer — 1 operation(s) for message.

TrustBoost PII Sanitizer Sanitize API

The Sanitize API from TrustBoost PII Sanitizer — 2 operation(s) for sanitize.

TrustBoost PII Sanitizer Score API

The Score API from TrustBoost PII Sanitizer — 1 operation(s) for score.

TrustBoost PII Sanitizer Verify API

The Verify API from TrustBoost PII Sanitizer — 1 operation(s) for verify.

Scroll for all 9

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

TrustBoost PII Sanitizer MCP Server

TrustBoost operates ONE remote MCP server at https://api.trustboost.dev/mcp, on the same host as its website, OpenAPI and agent card. It answers JSON-RPC 2.0 over plain HTTP POS...

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Trustboost Dev Plans Pricing

4 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Trustboost Dev Rate Limits

2 limits

RATE LIMITS

OpenAPI Overlays 1

Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.

Trustboost Dev Openapi Overlay

14 actions · documentation · trustboost-dev-openapi.json

GENERATED

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Trustboost Dev Authentication

0 schemes

SECURITY

Trustboost Dev Domain Security

TLSv1.3

SECURITY

Resources

Get Started 2

Portal, sign-up, and the first successful call

GettingStarted
GettingStarted
 Sandbox
Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

MCPServer
MCPServer
 WellKnown
WellKnown
 LLMsTxt
LLMsTxt
 AgentSkill
AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 DataModel
DataModel
 Conformance
Conformance
 Lifecycle
Lifecycle

Build 2

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 Packages
Packages

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity
DomainSecurity
 Authentication
Authentication

Operate 2

Status, limits, changes, and where to get help

Support
Support
 RateLimits
RateLimits

Commercial 4

Pricing, plans, and the legal terms of use

Pricing
Pricing
 PrivacyPolicy
PrivacyPolicy
 TermsOfService
TermsOfService
 Plans
Plans

Company 1

The organization behind the API

Website
Website

Other 7

Properties that don't map to a standard resource type

CapabilityMap
CapabilityMap
 Overlay
Overlay
 AgentCard
AgentCard
 DataSubjectRequest
DataSubjectRequest
 Subprocessors
Subprocessors
 DataResidency
DataResidency
 AITransparency
AITransparency

Scroll for all 7

Source (apis.yml)

apis.yml Raw ↑ 
aid: trustboost-dev
name: TrustBoost PII Sanitizer
description: 'TrustBoost PII Sanitizer is a pay-per-call "privacy firewall" for autonomous AI agent pipelines, built and operated
  by an individual developer (Teodoro Crispin, GitHub teodorofodocrispin-cmyk) and served entirely from https://api.trustboost.dev
  — the apex trustboost.dev has no DNS record. An agent POSTs text to /sanitize and gets it back with emails, phone numbers,
  national IDs (RFC, CUIT, CPF, CNPJ, Personalausweis, マイナンバー, NIR, Codice Fiscale, RRN and more across 8 languages), API
  keys and financial data replaced by [REDACTED], plus a safety_score, a risk_category and an entity list; five context modes
  (general, legal, financial, medical, code) tune the redaction. There is no account and no API key: 50 free calls per wallet
  with tx_hash=TRIAL, a free 3-per-hour preview, then x402 payment in USDC on Base or Solana ($0.01 per call or a 149 USDC
  prepaid bundle of 10,000), with every paid sanitization anchored on Solana as a verifiable "Proof of Sanitization". The
  same service is exposed three ways from one host: a 9-operation OpenAPI 3.0.0 REST contract, a remote MCP server at /mcp
  (one tool, sanitize_pii), and an A2A-flavored agent card at /.well-known/agent-card.json with three skills. The provider''s
  own privacy policy describes it as a learning prototype that sends raw text to OpenAI GPT-4o-mini for detection and has
  no certified security audit.'
url: https://raw.githubusercontent.com/api-evangelist/trustboost-dev/refs/heads/main/apis.yml
image: https://raw.githubusercontent.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/main/logo.png
x-type: company
x-source: harvest:a2a-registry
x-tier: profiled
x-tier-reason: enrichment pass 2026-09-19 (local-v3; was a2a-registry harvest stub)
specificationVersion: '0.20'
created: '2026-09-19'
modified: '2026-09-19'
tags:
- Privacy
- PII Redaction
- Data Protection
- LLM Security
- AI Safety
- Agents
- A2A
- MCP
- x402
- Agentic Commerce
- Solana
- Compliance
- Agent-Native
tags_raw:
- Privacy
- PII redaction
- Data protection
- LLM security
- AI safety
- Agents
- A2A
- MCP
- x402
- Agent commerce
- Solana
- Compliance
- Agent-native
- Agent Commerce
- agent-native
apis:
- aid: trustboost-dev:trustboost-mcp-server
  name: TrustBoost MCP Server
  description: Remote Model Context Protocol server at https://api.trustboost.dev/mcp (HTTP JSON-RPC 2.0, protocol version
    2024-11-05, serverInfo trustboost 2.6.0). initialize and tools/list answer anonymously with one tool, sanitize_pii, whose
    schema is published under the non-standard key input_schema rather than the MCP inputSchema; resources/list and prompts/list
    return -32601. Paid use is gated by x402 (HTTP 402) or a tx_hash, not by authentication. A server card is served at /.well-known/mcp-server-card.json
    (with /.well-known/mcp.json 301ing to it), and the server is listed on Glama.
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/mcp
  tags:
  - MCP
  - Agent-Native
  - Privacy
  tags_raw:
  - MCP
  - agent-native
  - Privacy
  properties:
  - type: MCPServer
    url: mcp/trustboost-dev-mcp.yml
  - type: MCPServer
    name: TrustBoost MCP endpoint (HTTP JSON-RPC)
    url: https://api.trustboost.dev/mcp
  - type: ToolCrosswalk
    url: mcp/trustboost-dev-tool-crosswalk.yml
- aid: trustboost-dev:trustboost-a2a-agent
  name: TrustBoost A2A Agent
  description: 'Agent2Agent surface: an agent card served from https://api.trustboost.dev/.well-known/agent-card.json (version
    2.6.0, no protocolVersion, capabilities object of product flags, three skills — sanitize_pii, verify_proof, trustboost_score)
    and a POST /message/send route the provider calls its A2A endpoint. The route is a plain FastAPI handler that requires
    a top-level "message" body field and rejects a JSON-RPC 2.0 envelope with 422, so the transport is not A2A JSONRPC; the
    card is graded flavored in a2a/trustboost-dev-a2a.yml. An ANP agent-description document (did:web:api.trustboost.dev)
    is served alongside it.'
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/message/send
  tags:
  - A2A
  - Agent-Native
  - x402
  tags_raw:
  - A2A
  - agent-native
  - x402
  properties:
  - type: AgentCard
    url: a2a/trustboost-dev-a2a.yml
  - type: AgentCard
    name: A2A Agent Card (provider-hosted)
    url: https://api.trustboost.dev/.well-known/agent-card.json
- aid: trustboost-dev:trustboost-dev-budget-api
  name: TrustBoost PII Sanitizer Budget API
  description: The Budget API from TrustBoost PII Sanitizer — 1 operation(s) for budget.
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/mcp
  tags:
  - Budgets
  tags_raw:
  - Budget
  properties:
  - type: OpenAPI
    url: openapi/trustboost-dev-budget-api-openapi.yml
  - type: Documentation
    url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
  - type: APIReference
    url: https://api.trustboost.dev/openapi.json
- aid: trustboost-dev:trustboost-dev-health-api
  name: TrustBoost PII Sanitizer Health API
  description: The Health API from TrustBoost PII Sanitizer — 1 operation(s) for health.
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/mcp
  tags:
  - Health
  properties:
  - type: OpenAPI
    url: openapi/trustboost-dev-health-api-openapi.yml
  - type: Documentation
    url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
  - type: APIReference
    url: https://api.trustboost.dev/openapi.json
- aid: trustboost-dev:trustboost-dev-mcp-api
  name: TrustBoost PII Sanitizer MCP API
  description: The Mcp API from TrustBoost PII Sanitizer — 1 operation(s) for mcp.
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/mcp
  tags:
  - MCP
  tags_raw:
  - Mcp
  properties:
  - type: OpenAPI
    url: openapi/trustboost-dev-mcp-api-openapi.yml
  - type: Documentation
    url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
  - type: APIReference
    url: https://api.trustboost.dev/openapi.json
- aid: trustboost-dev:trustboost-dev-message-api
  name: TrustBoost PII Sanitizer Message API
  description: The Message API from TrustBoost PII Sanitizer — 1 operation(s) for message.
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/mcp
  tags:
  - Message
  properties:
  - type: OpenAPI
    url: openapi/trustboost-dev-message-api-openapi.yml
  - type: Documentation
    url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
  - type: APIReference
    url: https://api.trustboost.dev/openapi.json
- aid: trustboost-dev:trustboost-dev-sanitize-api
  name: TrustBoost PII Sanitizer Sanitize API
  description: The Sanitize API from TrustBoost PII Sanitizer — 2 operation(s) for sanitize.
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/mcp
  tags:
  - Sanitize
  properties:
  - type: OpenAPI
    url: openapi/trustboost-dev-sanitize-api-openapi.yml
  - type: Documentation
    url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
  - type: APIReference
    url: https://api.trustboost.dev/openapi.json
- aid: trustboost-dev:trustboost-dev-score-api
  name: TrustBoost PII Sanitizer Score API
  description: The Score API from TrustBoost PII Sanitizer — 1 operation(s) for score.
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/mcp
  tags:
  - Score
  properties:
  - type: OpenAPI
    url: openapi/trustboost-dev-score-api-openapi.yml
  - type: Documentation
    url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
  - type: APIReference
    url: https://api.trustboost.dev/openapi.json
- aid: trustboost-dev:trustboost-dev-verify-api
  name: TrustBoost PII Sanitizer Verify API
  description: The Verify API from TrustBoost PII Sanitizer — 1 operation(s) for verify.
  humanURL: https://api.trustboost.dev/
  baseURL: https://api.trustboost.dev/mcp
  tags:
  - Verify
  properties:
  - type: OpenAPI
    url: openapi/trustboost-dev-verify-api-openapi.yml
  - type: Documentation
    url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
  - type: APIReference
    url: https://api.trustboost.dev/openapi.json
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: CapabilityMap
  url: capabilities/trustboost-dev-capability-edges.yml
  name: TrustBoost PII Sanitizer Business Capability Map
- type: Overlay
  url: overlays/trustboost-dev-openapi-overlay.yaml
- type: DomainSecurity
  url: security/trustboost-dev-domain-security.yml
- type: Website
  url: https://api.trustboost.dev/
- type: Documentation
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
- type: GettingStarted
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/blob/main/AGENTS.md
- type: APIReference
  url: https://api.trustboost.dev/openapi.json
- type: Pricing
  url: https://api.trustboost.dev/pricing.md
- type: PrivacyPolicy
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/blob/main/PRIVACY.md
- type: TermsOfService
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/blob/main/PRIVACY.md
- type: Support
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/issues
- type: GitHubOrganization
  url: https://github.com/teodorofodocrispin-cmyk
- type: AgentCard
  url: a2a/trustboost-dev-a2a.yml
- type: MCPServer
  url: mcp/trustboost-dev-mcp.yml
- type: WellKnown
  url: well-known/trustboost-dev-well-known.yml
- type: LLMsTxt
  url: llms/trustboost-dev-llms.txt
- type: AgentSkill
  url: skills/_index.yml
- type: Conventions
  url: conventions/trustboost-dev-conventions.yml
- type: ErrorCatalog
  url: errors/trustboost-dev-problem-types.yml
- type: DataModel
  url: data-model/trustboost-dev-data-model.yml
- type: RateLimits
  url: rate-limits/trustboost-dev-rate-limits.yml
- type: Plans
  url: plans/trustboost-dev-plans-pricing.yml
- type: Sandbox
  url: sandbox/trustboost-dev-sandbox.yml
- type: Conformance
  url: conformance/trustboost-dev-conformance.yml
- type: Lifecycle
  url: lifecycle/trustboost-dev-lifecycle.yml
- type: Packages
  url: packages/trustboost-dev-packages.yml
- type: Authentication
  url: authentication/trustboost-dev-authentication.yml
- type: DataSubjectRequest
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/blob/main/PRIVACY.md
- type: Subprocessors
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/blob/main/PRIVACY.md
- type: DataResidency
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/blob/main/PRIVACY.md
- type: AITransparency
  url: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/blob/main/PRIVACY.md
x-enrichment:
  date: '2026-09-19'
  status: enriched
  artifacts_added: 28
  pass: local-v3

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this
  • find_providersBrowse and filter every provider in the catalog.
  • get_provider_artifactsEvery artifact this provider publishes, grouped by type.
  • get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
  • get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
  • get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
  • get_provider_ratingPRO — composite, band, trend and facet scores.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This provider 
curl "https://apis.io/api/v1/providers/trustboost-dev"
All providers 
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose 
curl "https://apis.io/api/v1/providers/trustboost-dev/operations?limit=25"
How their score was established 
curl "https://apis.io/api/v1/providers/trustboost-dev/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.