ai-netcafe

Name: ai-netcafe
Author: com.ainetcafe

MCP serverMCP

Tables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.

Until 2026-09-25 this record combined several servers published from one repository. The others now have records of their own: netcafe-devkit, netcafe-docflow, netcafe-memory, netcafe-tables, netcafe-translate, netcafe-build, netcafe-almanac, netcafe-china, netcafe-docs, netcafe-images, netcafe-live-data, netcafe-tasks. Checks from before that date include them.

by com.ainetcaferepository ↗homepage ↗v1.7.0MIT

Is this yours?

This record is unclaimed

Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.

Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"ai-netcafe","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.

Claim this record

Observed by Wellknown

Evidence

Everything here was measured by our prober or read from a registry. Nothing is self-reported.

30-day availability164/169 checks ok

Tools observed via MCP handshake

what_can_you_do — Describe a task in plain language (any language) and get back exactly which tools on this server do it, with ready-to-run example calls — instead of reading the
list_apps — List the open-source AI applications hosted and ready to run at AI NetCafé (ainetcafe.com). Each one normally requires local setup (Docker/Python + your own mod
get_app — Full details of one hosted application: what it does, how to use it, measured benchmark scores, source repository, and the URL a human can open to run it. Examp
ask_model — Send a prompt to one specific large language model and get the answer plus measured platform cost metadata. The beta platform covers the user charge ($0.00); ca
compare_models — Run one prompt across multiple LLMs in parallel and return every answer side by side with measured platform cost metadata and latency. The beta platform covers
list_models — List every model currently available in the free beta with reference input/output rates and health metadata. Those rates are platform cost metadata only; every
remember — Persist a durable memory: an architecture decision, a stable user preference, a verified bug fix, or an important discovery. The free beta provides a bounded pe
recall — Retrieve previously stored memories, optionally filtered by search query and/or project. Call at the start of work on a known project to restore context: why de
web_search — Search the live web through a self-hosted SearXNG meta-search (aggregates dozens of engines, no tracking). Returns titles, URLs and snippets. Use when you need
fetch_page — Fetch a public URL and return clean LLM-ready Markdown from the server-rendered response. This tool does not execute browser JavaScript; for SPA or empty-text p
model_costs — Measured platform cost metadata for one call on each model; your charge is $0.00 during the free beta. Vendors publish per-million-token list prices, but a call
ai_visibility — Audit a URL for AI visibility: which AI crawlers robots.txt actually allows (parsed per user-agent group, not keyword-matched), whether llms.txt / sitemap / JSO
pdf_to_markdown — Convert a PDF (or a scanned page image) into clean Markdown that keeps headings, lists and tables, and puts multi-column pages in the right reading order. Text-
extract_tables — Extract tables from a PDF into structured rows (JSON + CSV). Pass fields to force a fixed set of columns — that aligns a pile of documents that each name their
extract_statement — Turn a bank statement or transaction PDF into a clean transaction table (JSON + CSV), then cross-check it: opening + credits - debits must equal the stated clos
json_yaml — Converts JSON to YAML or YAML to JSON. It works out which one you gave it, so you do not have to say. A parse failure comes back with the parser message instead
validate_json — Checks that text parses as JSON, and optionally that required keys are present with the right top-level types. Returns the specific violations, not just true/fa
diff_text — Returns which lines were added and which were removed, with line numbers — computed with a longest-common-subsequence, not guessed by a model. Use to compare tw
jwt_decode — Decodes the header and payload of a JWT and reports issued-at / expiry as readable timestamps plus seconds remaining. The signature is NOT verified and the resp
regex_test — Runs a regular expression against sample text and returns every match with its position and capture groups (named groups included). Use before wiring a pattern
diff_tables — Matches rows across two CSVs on a key column and reports three things: keys only in A, keys only in B, and keys in both whose other columns disagree — naming th
clean_table — Tidies a spreadsheet export: removes duplicate rows, trims whitespace (half-width and full-width — Chinese exports are full of 　), unifies the half-dozen ways a
merge_tables — Combines up to 20 CSVs into a single table. Headers do not have to match: columns are unioned and a file missing a column contributes blanks for it, so rows nev
reconcile_ledger — Reconciles two sets of records — your books against a bank, platform, or supplier statement. Matches rows on a key column, compares an amount column, and return
extract_invoices — Give it up to 20 invoice URLs (PDF or page images) and get back one table ready to post: number, date, seller, buyer, net / tax / gross, currency. Every row is
create_task — Create a task that runs on a schedule in our cloud — you do not keep anything running. It only notifies you when the result actually changes. Kinds: watch_page
list_tasks — Show scheduled tasks, next run times, run counts, and measured platform cost metadata. User charge is $0.00 during the beta.
get_task_runs — Recent runs of one scheduled task: what it returned, whether the result changed, and measured platform cost metadata. User charge is $0.00.
delete_task — Stop and remove a scheduled task and its run history.
transpile_sql — Convert a SQL statement from one dialect to another — mysql, postgres, sqlite, tsql, oracle, snowflake, bigquery, redshift, spark, hive, presto, trino, duckdb,
china_reachability — Fetch a URL from a real mainland-China network egress and report HTTP status, latency and China DNS resolution. Answers "is my site/API usable from China?" with
render_diagram — Turn diagram-as-code into an image: Mermaid, PlantUML, Graphviz/DOT, C4, Excalidraw and 20+ more (self-hosted Kroki). Returns a hosted SVG/PNG URL you can embed
check_job — Get the status or result of a job started by deep_research, translate_pdf, or make_slides. Poll every 15-30 seconds until status is "done" or "error". While wor
build_app — Turn one plain-language description into a LIVE single-page web tool: code is generated, deployed to managed hosting with HTTPS, and listed — you get the public

Provenance

Where this record came from

Every source is kept verbatim. Field changes are logged as events.

Official MCP Registrycom.ainetcafe/ai-netcafe

first seen 2 mo ago · fetched 2 d agoopen ↗

PyPIai-netcafe

first seen 2 mo ago · fetched 3 d agoopen ↗

Field history (12 recent events)

29 d ago · declared · summary → "Tables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready."
29 d ago · declared · version → "1.7.0"
29 d ago · declared · description → "Tables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready."
29 d ago · declared · name → "ai-netcafe"
1 mo ago · declared · summary → "JSON/YAML, regex, diff, JWT, SQL dialects — the keyless millisecond ops an agent needs mid-task."
1 mo ago · declared · description → "JSON/YAML, regex, diff, JWT, SQL dialects — the keyless millisecond ops an agent needs mid-task."
1 mo ago · declared · name → "netcafe-devkit"
1 mo ago · declared · summary → "Translation that never breaks structure: .srt timings, i18n key trees, PDF layout."
1 mo ago · declared · description → "Translation that never breaks structure: .srt timings, i18n key trees, PDF layout."
1 mo ago · declared · name → "netcafe-translate"
2 mo ago · declared · license → "MIT"
2 mo ago · observed · packageFacts → {"name":"ai-netcafe","registry":"pypi","publishedAt":"2026-08-21T01:40:29.653583Z","latestVersion":"1.6.1"}

when	check	result	http	latency	detail
4 d ago	mcp initialize	failed	530	26 ms	http 530
7 d ago	mcp initialize	failed	530	24 ms	http 530
10 d ago	mcp initialize	failed	530	21 ms	http 530
11 d ago	mcp initialize	failed	530	22 ms	http 530
11 d ago	mcp initialize	failed	530	21 ms	http 530
11 d ago	mcp initialize	ok	200	698 ms	server ai-netcafe 1.5.0 · protocol 2025-06-18 · 34 tools
12 d ago	mcp initialize	ok	200	680 ms	server ai-netcafe 1.5.0 · protocol 2025-06-18 · 34 tools
12 d ago	mcp initialize	ok	200	719 ms	server ai-netcafe 1.5.0 · protocol 2025-06-18 · 34 tools
12 d ago	mcp initialize	ok	200	759 ms	server ai-netcafe 1.5.0 · protocol 2025-06-18 · 34 tools
12 d ago	mcp initialize	ok	200	689 ms	server ai-netcafe 1.5.0 · protocol 2025-06-18 · 34 tools

ai-netcafe

This record is unclaimed

Evidence

What the publisher says

Capabilities

Where this record came from