# PXL8 verified fight records (remote · api.pxl8.io) Verified fight records for AI assistants: look up a fighter or fight card, cite the pxl8.io page. - Trust score: 81/100 (high trust) - Change this week: +3 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-02 ## Components - remote · `api.pxl8.io`: 81/100 (this document), [markdown](https://verifymcp.io/servers/io-pxl8-records/sports-data-mcp.md), [page](https://verifymcp.io/servers/io-pxl8-records/sports-data-mcp) ## Channel facts - Endpoint: `https://api.pxl8.io/sports-data/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `1.0.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-02. - **Endpoint Security**: 80/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 78/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 1660 tokens (~184/item across 9 items; 7 tools + 2 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 47/100 - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the PXL8 verified fight records MCP server? PXL8 verified fight records is a hosted endpoint at https://api.pxl8.io/sports-data/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http io-pxl8-records 'https://api.pxl8.io/sports-data/mcp' ``` ### Cursor ```json { "mcpServers": { "io-pxl8-records": { "url": "https://api.pxl8.io/sports-data/mcp" } } } ``` ### VS Code ```json { "servers": { "io-pxl8-records": { "type": "http", "url": "https://api.pxl8.io/sports-data/mcp" } } } ``` ### Codex ```toml [mcp_servers.io-pxl8-records] url = "https://api.pxl8.io/sports-data/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "io-pxl8-records": { "type": "remote", "url": "https://api.pxl8.io/sports-data/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add io-pxl8-records --url 'https://api.pxl8.io/sports-data/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: io-pxl8-records: url: "https://api.pxl8.io/sports-data/mcp" ``` ### Netclaw ```json { "McpServers": { "io-pxl8-records": { "Transport": "http", "Url": "https://api.pxl8.io/sports-data/mcp" } } } ``` ### Vellum ```bash assistant mcp add io-pxl8-records -t streamable-http -u 'https://api.pxl8.io/sports-data/mcp' ``` ### Other ```json { "mcpServers": { "io-pxl8-records": { "type": "http", "url": "https://api.pxl8.io/sports-data/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-02 (score 81, +1) No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-30 (score 80, 0) - [security] Tool “fetch” rewrote its description, which is the text the model reads - [cosmetic] “fetch” reworded the description of “id” ### 2026-09-29 (score 80, +1) No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-28 (score 79, 0) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-09-27 (score 79, +1) No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-25 (score 78, +1) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-09-23 (score 77, +1) No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-22 (score 76, +1) - [security] Resource “about” now points somewhere else: pxl8://about → pansofica://about - [security] Resource “terms” now points somewhere else: pxl8://terms → pansofica://terms - [security] The server changed its declared name: pxl8-records → pansofica-records - [security] Tool “fetch” rewrote its description, which is the text the model reads - [security] Tool “find_fighter” rewrote its description, which is the text the model reads - [security] Tool “find_subject” rewrote its description, which is the text the model reads - [security] Tool “get_event_card” rewrote its description, which is the text the model reads - [security] Tool “get_fighter_record” rewrote its description, which is the text the model reads - [security] Tool “get_subject” rewrote its description, which is the text the model reads - [security] Tool “search” rewrote its description, which is the text the model reads - [functional] Server version: 1.0.0 → 1.3.0 - [cosmetic] “search” reworded the description of “query” ## MCP tools (7) ### `find_fighter` (~209 tokens) Find a fighter 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. Input parameters: - `discipline` (string): Narrow to one discipline - `name` (string, required): The fighter's name, or the first characters of it - `place` (string): A hometown city, state/region or country to narrow the match ### `get_fighter_record` (~258 tokens) Get a verified fighter record 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. Input parameters: - `slug` (string, required): The fighter page's slug — the last part of its canonical URL ### `get_event_card` (~155 tokens) Get an event card 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. Input parameters: - `slug` (string, required): The event page's slug — the last part of its canonical URL ### `find_subject` (~211 tokens) Find a person or an organization 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. Input parameters: - `kind` (string): Narrow to people or to organizations - `name` (string, required): The person's or the organization's name, or the first characters of it ### `get_subject` (~257 tokens) Get the record of a person or an organization 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. Input parameters: - `handle` (string, required): The record's handle — the last part of its page URL - `kind` (string, required): person or organization ### `search` (~205 tokens) Search records 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. Input parameters: - `query` (string, required): A person's, an organization's or a fighter's name, or the first characters of it (at most 200 characters) ### `fetch` (~330 tokens) Fetch one record Read one record by the id search returned (person:, organization:, fighter:, parcel:/, provider:, chrb_ruling:, cpsc_recall:, fdic_institution:, khrc_ruling:, vehicle_manufacturer:, exclusion: or fda_device_recall:). 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. Input parameters: - `id` (string, required): An id from search: person:, organization:, fighter:, parcel:/, provider:, chrb_ruling:, cpsc_recall:, fdic_institution: