AbuseIPDB vs VirusTotal

AbuseIPDB 38

Read as a closed service with an official MCP server. The newest dated change to the surface is the MCP server's v0.1.1 on 2 August 2026, 93 days before the check; the API docs and blog carry no later date (10 of 30). One release in the last 90 days, v0.1.1 fell just outside it (0 of 20). Support is a contact form with no guaranteed response on the free plan, there is no public changelog for the API, and the MCP repository shows a pull request merged on 2 August but GitHub's issue pages could not be read (5 of 15). The MCP server sits in the official registry under io.github.abuseipdb (15). The MCP package has CI on Python 3.11 to 3.14 with ruff, pytest and a packaging check, and a locked dependency set (8 of 10). 10 + 0 + 5 + 15 + 8 = 38.

VirusTotal 88

Read as a closed service with open agent tooling. vt-mcp 0.9.9 on PyPI on 11 October 2026 and the repository's newest tag, antigravity-plugin-v0.1.1, on 2 November 2026 (30). Nine vt-mcp releases between 20 September and 11 October 2026 and 146 commits in 90 days (20). Pull requests merged within a day by the maintainer in October, weekly blog posts, dated release notes per version, but issue replies could not be read because github.com refuses our reader (15 of 25). io.github.VirusTotal/virustotal-mcp in the official registry, latest 0.9.9, and vt-py and vt-go as official clients (15). CI, PyPI, release and registry workflows in the MCP repository and a pinned mcp==2.1.1, while vt-py's last release is 28 October 2025 and Google's gti-mcp still requires mcp below 2.0 (8 of 10). 30 + 20 + 15 + 15 + 8 = 88.

AbuseIPDB 37

One API key per account with no scopes found, recommended in a Key header but also accepted as a query or form parameter per the docs (20 less 10 for the query string, so 10). The same key submits reports, bulk reports and clear-address deletes, with no read-only key; the official MCP server is read-only and its write-tool switch is inert (10 of 20). check and reports return reporter comments, which are public user-submitted text, and no guidance on treating them as untrusted was found (4 of 15). Paid plans include API log downloads for the last 24 to 120 hours and the pricing page lists the window per plan (10 of 15). security.txt returns 404, no disclosure policy, bug bounty or certification was found, and the MCP repository's SECURITY.md points to the vendor's support channels (3 of 20). 10 + 10 + 4 + 10 + 3 = 37.

VirusTotal 69

A personal v3 key carries every privilege of the account, with no scopes, sent only in an x-apikey header. Licensed groups get service accounts with six roles and a daily cap each. VTAI MCP uses OAuth with three scopes, vt:reports:read, vt:submissions:write and vt:network-analysis:write, and REST agent tokens are revocable with one DELETE. No documented query-string option (24 of 30). The read scope and readOnlyHint tools give a read-only mode; submission tools have no per-call confirmation of their own, so consent rests on the client and the X-VTAI-Consent header (15 of 20). Reports carry third-party text and ai_insights, and the VTAI pages say to treat report text as data, not instructions, and never to read a missing report as safety (12 of 15). Group administrators see consumption by endpoint and by user, VTAI shows OAuth connections at /oauth/connections, and no per-call log for a personal key was found (8 of 15). SECURITY.md in the MCP repository points to the Google Bug Hunters form, and the SecOps SLA and privacy notice are Google Cloud documents, but www.virustotal.com has no security.txt and whether VirusTotal is in scope of Google Cloud's SOC 2 and ISO 27001 reports could not be read (10 of 20). 24 + 15 + 12 + 8 + 10 = 69.

AbuseIPDB 75

Read with the hosted lines. A status page on UptimeRobot is linked from every page's footer (20). Its monitors and 90-day history load by script and answered with an error on 3 November 2026, so no incident record could be read (5). Daily limits are published per endpoint and per plan, 1,000 checks a day on the free plan up to 50,000 on Premium (15). A 429 carries Retry-After, X-RateLimit-Limit, X-RateLimit-Remaining and X-RateLimit-Reset, and a repeated report of the same address with the same comment within 24 hours updates the earlier report instead of adding one (15). The terms carry a service level agreement with a 99 per cent monthly availability target and a refund as the sole remedy (10). API v2 is generally available, with only the reports endpoint in open beta (10). 20 + 5 + 15 + 15 + 10 + 10 = 75.

VirusTotal 55

Read with the hosted lines, on the v3 API and VirusTotal AI together. No status page found. status.virustotal.com does not resolve and neither docs.virustotal.com nor ai.virustotal.com links one (0). No readable incident history (5). Rate limits documented with numbers, 4 requests a minute and 500 a day on a public key, and 60 queries per 60-second window and 1,000 a UTC day plus 20 uploads a minute and 500 a day on VTAI (15). 429 answers QuotaExceededError or TooManyRequestsError on v3, the quota FAQ says wait 30 to 60 seconds, VTAI says honour Retry-After, and VTAI submissions are idempotent by SHA-256 receipt or a caller-chosen request_id (15). The Google Cloud SecOps SLA page lists service level agreements for Google Threat Intelligence and VirusTotal, which cover paid licences (10). The v3 API is generally available; VTAI's OpenAPI document is version 0.10.39 and vt-mcp 0.9.9, neither marked beta, with Codex support marked staging (10). 0 + 5 + 15 + 15 + 10 + 10 = 55.

AbuseIPDB 59

The surface graded is the REST API v2, with the official MCP server noted. No OpenAPI document was found. The MCP server's two tools carry JSON Schema inputs with range constraints from pydantic Field (8 of 25). llms.txt on abuseipdb.com describes the API, endpoints, categories and reporting rules (10). Each endpoint has a purpose statement and a parameter table, the FAQ explains scoring and decay, and the docs say to act on abuseConfidenceScore rather than isWhitelisted, with little on when not to call (14 of 20). Parameters give defaults and ranges (maxAgeInDays 1 to 365, perPage 1 to 100), usageType has a listed set of values and categories are numbered, but types are not stated and the categories default is ambiguous (10 of 15). Examples in cURL, Python, PHP, C# and VBScript for every endpoint, and errors follow the JSON API shape with 422, 429 and 402 examples (12 of 15). v2 is in the path, there is no API changelog, the blog's last post is from December 2018, and the reports endpoint may change without notice (5 of 15). 8 + 10 + 14 + 10 + 12 + 5 = 59.

VirusTotal 77

VTAI publishes an OpenAPI 3.1 document at ai.virustotal.com/openapi.json with 17 operations, and the MCP tools take typed JSON Schema inputs with annotations. No OpenAPI document was found for the v3 API, whose reference lists typed parameters page by page (20 of 25). llms.txt on both hosts, 650 links on virustotal.readme.io and an agent manifest plus a Markdown quickstart at /skills/BASIC.md on ai.virustotal.com (10). VTAI descriptions and skills say when to look up, when not to submit, and what a missing report does not prove. v3 endpoint descriptions are one line, such as "Retrieve information about a file" (15 of 20). Enums for indicator_type, analysis status, pending_reason and rejection codes, a consent header fixed to standard-v1, required path parameters. The v3 pages read carry no constraints beyond the hash formats (11 of 15). 16 documented v3 error codes with HTTP statuses and a JSON envelope, and VTAI documents 401, 404 and 429 per operation, but the v3 file report page read shows no example request or response body (11 of 15). Version in the path (v3, with v2 still served) and dated release notes for vt-mcp, but no changelog for the API itself (10 of 15). 20 + 10 + 15 + 11 + 11 + 10 = 77.

AbuseIPDB 30

No x402, MPP or L402 (0). Plan prices are public, $25 and $99 a month, sold by daily quota rather than per call (10). The Individual plan allows 1,000 checks a day with no card, and paid plans carry a 30-day trial (20). The key comes from the account page after a browser signup, and the terms forbid multiple accounts to raise quota, so no autonomous route (0). 0 + 10 + 20 + 0 = 30.

VirusTotal 40

No x402, MPP or L402 (0). Premium quotas and Google Threat Intelligence are sold by contacting sales, and no price was found on any page read (0). A public key gives 500 requests a day and VTAI 1,000 a day, with no card (20). An agent registers itself with POST /api/v3/agents/register and receives a token in the response, no browser or person involved (20). 0 + 0 + 20 + 20 = 40.

AbuseIPDB 74

check returns a compact record unless verbose is set, which adds the reports array, maxAgeInDays bounds the window, and blacklist takes a limit and a plaintext form (18 of 25). reports is paginated with page and perPage up to 100 and next and previous links, and blacklist filters by confidence, country and IP version, though check has no field selection (16 of 20). Errors carry a status and a detail an agent can act on, 429 names the daily limit and the headers say when it resets, and a 402 marks a plan limit on check-block (16 of 20). Every lookup is a GET, duplicate reports within 24 hours collapse, and both MCP tools are annotated readOnlyHint and idempotentHint (16 of 20). One required parameter per endpoint with sensible defaults. No official SDK beyond a Laravel package in the vendor's GitHub organisation and the Python MCP server (8 of 15). 18 + 16 + 16 + 16 + 8 = 74.

VirusTotal 83

The hosted MCP server lists 11 compact tools, one over the ten-tool line (15), and the vt:reports:read OAuth scope gives a read-only subset (5 added back, so 20). VTAI reports are fixed in shape with detections as labels, category counts and coverage sized for a model. Pagination and field selection on v3 list endpoints were not read in this run (10 of 20). Error codes an agent can branch on, QuotaExceededError, NotFoundError, receipt_conflict on 409, enumerated rejection codes, and Retry-After on VTAI 429s (18 of 20). File submissions are keyed by SHA-256 with recoverable receipts, network submissions by a persisted request_id, can_resubmit is set on every result, and all 11 tools carry readOnlyHint and destructiveHint in the source (20). Few required parameters, official clients vt-py and vt-go, and the submit_local_file stdio tool (15). 20 + 10 + 18 + 20 + 15 = 83.