PXL8 verified fight records
Server Details
Verified fight records for AI assistants: look up a fighter or fight card, cite the pxl8.io page.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
The `fetch` tool reads any record by id (person:, fighter:, event:, etc.), directly overlapping with `get_subject`, `get_fighter_record`, and `get_event_card`, which each read one record of those same kinds. Similarly, `search`, `find_fighter`, and `find_subject` all resolve names to records, so an agent has three plausible entry points for the same intent with unclear boundaries.
All names are snake_case, but the conventions are mixed: bare verbs (`fetch`, `search`) sit alongside `find_*` and `get_*` prefixes used for essentially the same retrieval operation (find_fighter vs get_fighter_record), and the get/find split does not map to a meaningful distinction.
Seven tools is a reasonable, well-scoped count for a lookup service, and each tool maps to a recognizable operation. The count could arguably be lower since the generic `fetch` subsumes the three `get_*` tools, but nothing feels bloated.
Core lookups (name resolution, single-record retrieval, event cards) are covered, but there is no way to list or browse fighters, events, or records by commission/promotion, and the server's stated purpose (fight records) is only half the surface since three tools serve Pansofica person/organization records instead.
Available Tools
7 toolsfetchFetch one recordARead-onlyIdempotentInspect
Read one record by the id search returned (person:, organization:, fighter:, hypd:, event:, golden_gloves:, parcel:/, provider:, au_company:<subject_key>, chrb_ruling:<subject_key>, cpsc_recall:<subject_key>, eu_sanction:<subject_key>, eu_tender_notice:<subject_key>, fdic_institution:<subject_key>, legal_entity:<subject_key>, jp_corporation:<subject_key>, khrc_ruling:<subject_key>, vehicle_manufacturer:<subject_key>, exclusion:<subject_key>, fda_device_recall:<subject_key>, sg_entity:<subject_key>, company:<subject_key>, uk_contracts_finder_notice:<subject_key>, uk_tender_notice:<subject_key>, uk_sanction:<subject_key>, significant_control:<subject_key>, facility:<subject_key>, motor_carrier:<subject_key>, contract_notice:<subject_key> or restricted_party:<subject_key>). Answers { id, title, text, url, metadata } as one JSON document; metadata carries kind, recordStatus, citeAs and lastReviewed. The text presents facts in three separate grades, each its own list; a fact stated by the subject is the subject's own statement; a disputed fact remains present, marked Disputed. The url and the citeAs line in metadata identify the page for attribution. Each result carries its url and the citeAs attribution line in metadata; a disputed fact remains in the answer, marked with the word Disputed. This is the lookup tier that needs no key (rate-limited per client and in total); keyed partner access with higher limits exists.
Inputs: id (required).
find_fighterFind a fighterARead-onlyIdempotentInspect
Resolve a fighter's name (optionally with a hometown or region and a discipline) to candidate fighter pages on https://pxl8.io. Answers at most 5 candidates, each with a confidence band, the bouts on file, its canonical page URL and its slug. The name must be at least 3 characters. Every result carries its canonical page URL (canonicalUrl) and a citeAs attribution line. A tally or bout count is a count of bouts on file from the earliest date on file — it is not a career record. Results are as published by the named athletic commissions and federations. This is the lookup tier that needs no key (rate-limited per client and in total); keyed partner access with higher limits exists.
Inputs: name (required), place, discipline.
find_subjectFind a person or an organizationARead-onlyIdempotentInspect
Resolve the name of a person or an organization to published records on https://pansofica.com — records whose subject proved who they are and reviewed what is said about them. Answers at most 5 candidates (the name must be at least 3 characters), each carrying its handle and kind. This is a lookup, not a list. The facts come in three separate grades, each its own list, never one merged list or count: facts from a registry document, facts from the open web, and facts stated by the subject. A fact stated by the subject is the subject's own statement, not a confirmation; a disputed fact remains in the answer, marked Disputed, with no reason attached. This is the lookup tier that needs no key (rate-limited per client and in total); keyed partner access with higher limits exists.
Inputs: name (required), kind.
get_event_cardGet an event cardARead-onlyIdempotentInspect
A published event card (https://pxl8.io/event/): promotion, date, venue, status and the bouts in order, with each corner's name and fighter page where one exists. Every result carries its canonical page URL (canonicalUrl) and a citeAs attribution line. A tally or bout count is a count of bouts on file from the earliest date on file — it is not a career record. Results are as published by the named athletic commissions and federations. This is the lookup tier that needs no key (rate-limited per client and in total); keyed partner access with higher limits exists.
Inputs: slug (required).
get_fighter_recordGet a verified fighter recordARead-onlyIdempotentInspect
The verified record for one fighter page (https://pxl8.io/), exactly as the public page states it: every bout on file with its date, result, method, the commission that published it and the sha256 of that document, plus a tally labelled "on file from ". Where the reported grade is released, it is returned as a SEPARATE list that is never added to the verified tally. The record and every bout carry a record status (verified, confirmed by the athlete, corrected at the athlete's request, or disputed) with the date it was last reviewed; a disputed bout stays in the list — the status says only that it is disputed, never why. Every result carries its canonical page URL (canonicalUrl) and a citeAs attribution line. A tally or bout count is a count of bouts on file from the earliest date on file — it is not a career record. Results are as published by the named athletic commissions and federations. This is the lookup tier that needs no key (rate-limited per client and in total); keyed partner access with higher limits exists.
Inputs: slug (required).
get_subjectGet the record of a person or an organizationARead-onlyIdempotentInspect
One published record (https://pansofica.com/ for a person, https://pansofica.com/org/ for an organization), exactly as its public page states it: the facts in three separate lists by grade, each fact with its field, value, sources and status, plus the record status and when it was last reviewed. A fact from a registry document or from the open web carries a status (verified, reported, confirmed by the subject, or disputed); a fact stated by the subject carries NO status — it is a statement, not a confirmation. The facts come in three separate grades, each its own list, never one merged list or count: facts from a registry document, facts from the open web, and facts stated by the subject. A fact stated by the subject is the subject's own statement, not a confirmation; a disputed fact remains in the answer, marked Disputed, with no reason attached. This is the lookup tier that needs no key (rate-limited per client and in total); keyed partner access with higher limits exists.
Inputs: kind (required), handle (required).
searchSearch recordsARead-onlyIdempotentInspect
Search Pansofica records of people and organizations and pxl8.io fighter records by name. Each result carries an id in the form the fetch tool reads, and its url. Answers { results: [{ id, title, url }] } as one JSON document: at most 5 person or organization records first, then at most 5 fighter records; a query under 3 characters answers an empty list. A notice member says when one of the two sources could not be searched. This is a lookup, not a list. Each result carries its url and the citeAs attribution line in metadata; a disputed fact remains in the answer, marked with the word Disputed. This is the lookup tier that needs no key (rate-limited per client and in total); keyed partner access with higher limits exists.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
UFC fights since 2000, plus PFL and Bellator: results, round stats, fighters and odds. REST and MCP.
MMA MCP: UFC, PFL, BKFC, RIZIN, OKTAGON results, stats, rankings, scorecards. Free plan, no card.
Entity intelligence across AI surfaces. Read the verified record and submit corrections.
BJJ gym, coach, event, and city data for AI agents. Free base tools, x402-paid premium.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceGives AI clients free, keyless access to professional boxing data — upcoming cards, recent results, boxer profiles, division rankings, broadcasters, odds and win forecasts — so they can answer fight-night questions and cite a source page. Ships tools, resources and prompts covering schedules, bouts, rankings and search.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query UFC, PFL, and Bellator fight results, fighter profiles, round-by-round statistics, ratings, and sportsbook moneylines through a remote MCP server and REST API.MIT
- AlicenseNot gradedqualityBmaintenanceEnables an agent to query MMA data—fight schedules, results, per-round stats, rankings history, judges' scorecards, and consensus odds—across UFC and other promotions directly via Model Context Protocol.564 npmMIT
- AlicenseBqualityDmaintenanceProvides AI agents with live, grounded sports data including model probabilities, track records, and European soccer and tennis arbitrage opportunities, so they answer from real numbers instead of stale guesses.1368 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.