
API Acre MCP server
Which servers in the official MCP registry are API Acre's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-24
- Registry namecom.apiacre/api-acreverified in the MCP registry
The registry name sits under apiacre.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools73
- Server calls itselfapiacre
- Server version0.1.36
- Protocol version2025-06-18
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 175 ms.
- Its tools do every use case we checked: extract metadata from a public webpage URL; generate a JSON schema from sample records; convert CSV, JSON, and YAML records between formats.
- Checked on 3 of the 7 days it takes to judge reliability.
Once connected
- For "extract metadata from a public webpage URL", the likely first call is web.metadata.
- For "generate a JSON schema from sample records", the likely first call is data.schema.
- For "convert CSV, JSON, and YAML records between formats", the likely first call is data.convert.
- Its definitions take about 16023 tokens of context: enable only the tools a task needs.
- Parameters are untyped or undescribed in 47 of 73 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- What an agent can do with it3 of 3 use cases
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer507 ms
- Space in an agent's context≈ 16,023 tokensthe definitions of all its tools (73), which an agent carries on every turn
- Tool definitionsB · 89 of 100
- Typed results73 of 73 toolsdeclared outputSchema: results come typed, read once
- Parameters without a type: in 2 of 73
- Parameters without a description: in 47 of 73
What an agent can do with it
- can do · extract metadata from a public webpage URL
- can do · generate a JSON schema from sample records
- can do · convert CSV, JSON, and YAML records between formats
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
web.extractConvert and extract a public website URL into clean Markdown or readable text plus bounded structured links, canonical and heading signals, Schema.org types, redirect evidence, content hashes, and response provenance for RAG, research, or…
web.metadataExtract webpage metadata from one public URL: page title, meta description, canonical URL, headings, hreflang, icons, feeds, Open Graph, Twitter Cards, and JSON-LD Schema.org types, with redirect and response provenance plus privacy-safe…
web.seo-auditAudit one public URL for title, meta description, H1 count, image alt text, canonical, robots, language, Open Graph, Twitter cards, headings, hreflang, feeds, and Schema.org data; return a deterministic score and prioritized issue codes.
web.security-auditScan a public website for TLS and browser security header weaknesses and return a security score with fixes.
web.accessibility-auditCheck a public page for deterministic HTML accessibility problems and return actionable WCAG-oriented findings.
web.performance-profileMeasure website response latency, payload size, compression, caching, and performance signals for a public URL.
web.linksExtract and classify links from one public page or safely crawl up to 10 same-origin pages into an agent-ready site map with page provenance, depth limits, and robots.txt enforcement.
web.robots-sitemapInspect a domain's robots.txt crawl rules and XML sitemap health, availability, and URL count.
web.tech-fingerprintIdentify frameworks, analytics, CDNs, servers, and other website technologies from public response signals.
web.email-authCheck a public domain's email authentication and anti-spoofing posture using MX, SPF, DMARC, caller-selected DKIM, MTA-STS, TLS-RPT, and BIMI DNS evidence.
web.domain-intelligenceInvestigate a domain using parallel DNS, TLS certificate, RDAP (the standards-based successor to WHOIS), DNSSEC, SPF, and DMARC signals with factual findings and source provenance.
web.full-auditRun a comprehensive website audit combining SEO, security, accessibility, and performance scores with prioritized fixes.
web.business-due-diligenceAssess one public business website and domain using site quality, SEO, security, accessibility, performance, DNS, TLS, RDAP, and optional public GLEIF candidates; return technical evidence and explicit identity, ownership, compliance, and…
commerce.product-pricePaste one public retailer product URL to get its current publisher-supplied structured price, currency, availability, seller, shipping terms, aggregate rating, variant attributes, identifiers, observation time, and evidence hashes from…
research.lei-entity-searchSearch the official GLEIF Global LEI Index by exact LEI or legal name and return ranked legal-entity identity, registration, mapped-identifier, and relationship-availability evidence.
document.extractExtract clean text and metadata from supplied PDF, DOCX, HTML, Markdown, CSV, JSON, YAML, or plain-text documents.
document.tablesExtract structured table rows and columns from supplied HTML, DOCX, or CSV documents.
document.redactDeterministically detect and redact PII and personal data in supplied text with overlap-safe matching for emails, phone numbers, validated IPv4 and IPv6 addresses, Luhn-valid payment cards, valid-checksum IBANs, and structurally valid US…
document.diffCompare two texts and return structured line additions, removals, and a unified diff.
data.profileProfile CSV, TSV, JSON, JSON Lines, or YAML records for field types, nulls, uniqueness, and representative samples.
data.cleanClean CSV, TSV, JSON, JSON Lines, or YAML records with collision-safe header normalization, deterministic integrity hashes, and exact transformation counts.
data.convertConvert caller-supplied CSV, TSV, JSON, JSON Lines (NDJSON), or YAML with optional root preservation, deterministic integrity hashes, JSON-encoded nested tabular cells, and explicit rejection of ambiguous duplicate keys or non-finite…
data.json-repairRepair caller-supplied malformed JSON by safely removing an outer Markdown fence, comments, single-quoted strings, unquoted identifier keys, Python literals, and trailing commas, with transformation hashes and strict rejection of…
data.schemaCreate and generate a nested JSON Schema Draft 2020-12 contract by inferring field types and required fields from representative JSON, CSV, TSV, JSON Lines, or YAML records, with equivalent CSV/TSV numeric and null inference, input…
data.schema-validateValidate JSON data against a bounded JSON Schema Draft 2020-12 contract for nested objects, arrays, required properties, types, enums, formats, lengths, patterns, and numeric bounds; return deterministic instance and schema JSON Pointers…
data.contractNormalize caller-supplied CSV, TSV, JSON, JSON Lines, or YAML to deterministic JSON, infer a Draft 2020-12 schema from that normalized value, and validate one future JSON value in a single x402 call.
data.schemaorg-normalizeNormalize caller-supplied inline Schema.org JSON-LD into deterministic Organization, Product, Service, Article, and Event entities with privacy scrubbing and field-level evidence hashes.
data.deduplicateRemove duplicate CSV, TSV, JSON, JSON Lines, or YAML records using selected identity fields and report the removed count.
developer.x402-preflightProbe a public endpoint without paying, grade its x402 v2 challenge, check exact-host x402-list presence and traction, and optionally rank licensed market matches with buyer-concentration caveats.
developer.openapi-auditValidate and audit an OpenAPI document for missing operation IDs, descriptions, responses, and consistency problems.
developer.dependency-auditAudit exact Python/PyPI, npm, Go, Maven, NuGet, crates.io, or RubyGems dependencies against OSV and return affected packages and vulnerabilities.
developer.license-auditClassify software dependency licenses and flag packages that need commercial or legal review.
developer.secret-scanDetect likely leaked API keys, tokens, private-key headers, JWTs, and credential assignments in caller-supplied source or configuration text. Return type, line, fingerprint, and a fully redacted preview with no network access or code…
developer.code-metricsMeasure caller-supplied source code with Python AST analysis or a deterministic lexical fallback, including per-function complexity, a SHA-256 fingerprint, density ratios, syntax status, and actionable maintainability signals without…
developer.code-change-reviewCompare caller-supplied before and after source snapshots without execution or network access, returning source fingerprints, syntax regressions, structural deltas, function-level changes, and bounded review findings.
developer.sql-change-reviewStatically parse caller-supplied SQL without a database connection or execution, inventory statements and tables, and flag destructive DDL, unfiltered writes, and migration atomicity concerns.
developer.structured-diffCompare JSON or YAML deterministically and return source hashes plus machine-readable additions, removals, and replacements by path with explicit truncation evidence.
research.feed-normalizeFetch and normalize public RSS or Atom feeds into stable structured JSON entries for agents and research workflows.
research.news-aggregateMerge two to eight public RSS or Atom feeds into a filtered, deduplicated, time-ordered news stream with bounded partial-failure reporting.
developer.openapi-test-generateGenerate deterministic, syntax-validated pytest and requests smoke tests from a caller-supplied OpenAPI 3 document, with mutating operations disabled by default.
research.us-contract-searchSearch public USAspending prime federal procurement awards by recipient company or organization name, UEI, or legacy DUNS, returning bounded contract values, agencies, performance dates, descriptions, official award links, and explicit…
research.federal-register-searchSearch newest U.S. Federal Register document metadata by topic, agency, type, and publication date, returning bounded regulatory notices, rules, proposed rules, presidential documents, and links to FederalRegister.gov and official…
research.ofac-entity-searchCompare a business or organization name with separately named Entity records and aliases in the official OFAC SDN and Consolidated Non-SDN files, returning deterministic candidate scores, program tags, source hashes, and freshness…
research.organization-evidenceRetrieve a current supplier and organization evidence report from official GLEIF legal-entity, USAspending prime-contract, SEC filing-activity, and OFAC Entity records, with bounded source-specific coverage for procurement research and no…
data.vin-decodeDecode a full 17-character VIN into normalized NHTSA vPIC make, model, year, body, engine, transmission, plant, fuel, and occupancy fields with official source evidence and explicit missing-data semantics.
data.worldbank-snapshotBundle six official World Development Indicators into one normalized country snapshot with latest and previous GDP, growth, population, inflation, unemployment, and life-expectancy observations plus source and license evidence.
research.sec-filing-signalsLook up a public company by ticker or CIK, normalize recent SEC filings, and flag deterministic events such as late filings, amendments, auditor changes, non-reliance, control changes, or bankruptcy disclosures.
research.sec-insider-transactionsRetrieve recent SEC Form 4 officer, director, and 10% beneficial-owner trades for a ticker or CIK, including purchases, sales, awards, exercises, tax withholding, prices, holdings, 10b5-1 context, derivatives, and filing footnotes.
research.sec-financial-factsRetrieve normalized, recent issuer-reported revenue, earnings, balance-sheet, cash-flow, and diluted-EPS facts from official SEC XBRL data.
research.sec-company-evidenceResolve an exact SEC company name, ticker, or CIK, then bundle recent filing signals, normalized issuer-reported XBRL facts, and Form 4 insider transactions into one bounded public-company evidence report with explicit section coverage…
research.crossref-work-searchSearch open Crossref bibliographic metadata by title, author, DOI fragment, or citation and return bounded normalized publication, author, citation, license, and update metadata without abstracts or full text.
research.crossref-doi-metadataResolve one DOI into normalized open Crossref bibliographic, author, container, citation-count, license, identifier, and correction or retraction-link metadata without abstracts or full text.
research.wikidata-organization-searchSearch CC0 Wikidata organization candidates and normalize public websites, inception dates, company identifiers, entity types, countries, industries, headquarters, parent, founder, owner, subsidiary, and product links with explicit…
data.ecb-fx-referenceConvert an amount between two supported currencies using one validated ECB daily reference-rate observation. The underlying ECB statistics are available free from the ECB Data Portal; the fee covers bounded retrieval, validation, clearly…
data.place-geocodeResolve one global city or locality name into bounded, population-ranked GeoNames coordinates, country and first-level-region identity, population, timezone, feature code, and source freshness without a request-time network call.
data.reverse-geocodeResolve one latitude/longitude pair into bounded, great-circle-distance-ranked nearby GeoNames populated places with country, first-level region, population, timezone, feature code, and source freshness without a request-time network call.
data.us-address-geocodeGeocode one structural address in the United States, Puerto Rico, or U.S. Island Areas with normalized U.S. Census MAF/TIGER coordinates, optional bounded state/county/tract/block/congressional geography, exact source attribution, and…
data.current-weatherGet one current weather snapshot for a city/locality name or exact coordinates. Returns the nearest NOAA/NWS station observation where available; otherwise returns the latest MET Norway model point, always labeled explicitly as…
data.us-weather-forecastGet a global weather forecast for a city/locality name or exact coordinates. Returns normalized day/night or hourly periods worldwide: NOAA/NWS is preferred within supported U.S. coverage for optional station conditions and active alerts…
data.timezone-convertConvert an offset-aware ISO 8601 instant or a local wall time between IANA time zones with explicit DST gap and repeated-hour handling, nearby transition evidence, and a pinned local time-zone database.
The first 60 of 73, as the server listed them.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"api-acre": {
"type": "http",
"url": "https://apiacre.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http apiacre https://apiacre.com/mcpclaude.ai, ChatGPT and other clients: add https://apiacre.com/mcp as a custom connector in the settings.
OpenAPI spec
85 paths, read 2026-10-24. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.