mcp server

ai-netcafe

23 agent tools + a measured per-call model cost dataset. No key needed to start.

Description as published by the maintainer. Source

• version 1.4.0
• active

active — Most recent push to the repository was 2026-08-04.

What this server can do

23 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

ai_visibility(url)

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 / JSON-LD / canonical exist, and how much real text an agent gets without running JavaScript. Returns a score plus the specific fixes, ordered by impact. Required: url.

ask_model(model, prompt, system, max_tokens)

Send a prompt to one specific large language model and get the answer plus its exact cost in USD. Useful when you want a second opinion from a different model, or a cheaper model for a bulk subtask. Example — GET https://ainetcafe.com/t/ask_model?prompt=Say+hi&model=deepseek-v4-flash Required: prompt.

build_app(name, refine, visibility, description)

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 URL in ~1-2 minutes. Best for tool-style apps: calculators, converters, checklists, timers, generators, small games. Async — poll with check_job. Example — tools/call build_app {"description":"a tip calculator web app"} → poll check_job Required: description.

check_job(job_id)

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 work is pending, follow retry_after_seconds and next_action; when complete, prefer structured_result when present. Example — GET https://ainetcafe.com/t/check_job?job_id=<id-from-a-job-tool> Required: job_id.

china_reachability(url)

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 a measurement instead of a guess — you cannot get this from a VPS abroad. Required: url.

compare_models(models, prompt, system)

Run one prompt across multiple LLMs in parallel and return every answer side by side with its real measured cost and latency. This answers "which model should I actually use for this kind of task?" with data instead of guesswork — useful before committing a long job to an expensive model. Example — GET https://ainetcafe.com/t/compare_models?prompt=Explain+CAP+theorem+in+1+line Required: prompt.

create_task(kind, input, notify_url, interval_seconds)

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 (Watch a web page and report when its content changes); daily_answer (Re-run a web-researched question on a schedule and report when the answer changes); watch_reachability (Track whether a site stays reachable from mainland China). Needs a workspace token (?w=ws_... on your MCP URL) so you can manage it later. Required: kind, input.

delete_task(task_id)

Stop and remove a scheduled task and its run history. Required: task_id.

extract_statement(url)

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 closing balance. If it does not balance you get the exact difference and which row the running balance first breaks at — so you know whether the table is safe to use for accounting. Text-layer PDFs only (scanned images not yet supported). Required: url.

extract_tables(url, fields)

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 headers differently into one consistent table. Rows the model was unsure about are flagged rather than guessed. Text-layer PDFs only. Required: url.

fetch_page(url)

Fetch any public URL and return LLM-ready clean Markdown (rendered via Crawl4AI, handles JS pages). Use after web_search to read a source, or to ingest any page for analysis. Example — GET https://ainetcafe.com/t/fetch_page?url=https://example.com Required: url.

get_app(slug)

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. Example — GET https://ainetcafe.com/t/get_app?slug=<slug-from-list_apps> Required: slug.

get_task_runs(limit, task_id)

Recent runs of one scheduled task: what it returned, whether the result changed, and what each run cost. Required: task_id.

list_apps(category)

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 model API key); here they run pre-configured. Use this to find a tool for a task like translating a PDF with formulas intact, generating a PowerPoint file, polishing an academic paper, or running an autonomous research report. Do not call this first when the request already clearly matches compare_models, translate_pdf, deep_research, or make_slides; call that task tool directly. Example — GET https://ainetcafe.com/t/list_apps

list_models(tier)

List every model callable through AI NetCafé with its input/output price per million tokens, so you can pick by cost as well as capability. Example — GET https://ainetcafe.com/t/list_models

list_tasks

Show the scheduled tasks on this workspace, when each runs next, how many times it has run and what it has cost so far.

model_costs(days)

What one call actually costs on each model, measured. Vendors publish per-million-token list prices, but a call's cost depends on how many tokens the model chooses to emit — models differ by an order of magnitude on the same prompt. standard_bench sends an IDENTICAL prompt to every model, so the difference is the model, not the workload — use that to choose a model before bulk work. production_mixed is real traffic and is NOT comparable across models. Free to cite, CC BY 4.0. Example — GET https://ainetcafe.com/t/model_costs

pdf_to_markdown(url)

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-layer PDFs are read exactly and cost far less; images go through a vision model. Required: url.

recall(limit, query, project)

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 decisions were made, known fixes, preferences. Example — GET https://ainetcafe.com/t/recall?query=<what+to+remember> (needs a workspace/key for durable memory)

remember(kind, content, project)

Persist a durable memory: an architecture decision, a stable user preference, a verified bug fix, or an important discovery. Anonymous callers get a small per-network memory pool; callers sending an AllRouter key (Authorization: Bearer sk-...) get a large pool shared across ALL their machines and agents — the same key on a laptop's Claude Code and a desktop's Codex recalls the same memories. Do not store secrets or raw logs. Example — tools/call remember {"content":"Deploy key rotates monthly"} Required: content.

render_diagram(type, format, source)

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 directly in Markdown or HTML. Example — GET "https://ainetcafe.com/t/render_diagram?source=graph TD;A--%3EB&format=png" Required: source.

transpile_sql(sql, read, write)

Convert a SQL statement from one dialect to another — mysql, postgres, sqlite, tsql, oracle, snowflake, bigquery, redshift, spark, hive, presto, trino, duckdb, clickhouse, databricks, doris, starrocks and more. Deterministic parser (sqlglot), not an LLM: the same input always produces the same output, and syntax errors come back with the exact line and column. Use it when migrating queries between databases or debugging dialect-specific syntax. Required: sql, write.

web_search(query, max_results)

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 current information or sources. Example — GET https://ainetcafe.com/t/web_search?query=latest+MCP+spec Required: query.

Last successful function declaration observed on 2026-08-13. Source: https://ainetcafe.com/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://ainetcafe.com/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/mario03690/ai-netcafe
• Website — https://ainetcafe.com/mcp.html
• npm: ai-netcafe
• pypi: ai-netcafe
• Remote endpoint (streamable-http) — https://ainetcafe.com/mcp

Related, by what their authors tagged them

• Vaaya — last commit 2026-08-06, shares deep-research
  Pay-per-call agent superpowers: media/video gen, product demos, research, GTM, scraping, compute.
• io.github.capyBearista/gemini-researcher — archived, last commit 2026-06-01, shares deep-research
  Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage
• io.github.andreisirbu91-lab/mcpspend — last commit 2026-07-29, shares llm-cost
  Query your MCPSpend usage: cost today, top tools, recent sessions, budget projections.
• SkillFM Beacon — last commit 2026-05-20, shares llm-cost
  AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.
• SkillFM Beacon — last commit 2026-05-20, shares llm-cost
  AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.
• Soma — last commit 2026-08-06, shares agent-tools
  RMCP runtime for provider-backed agents with CLI, REST, HTTP MCP, plugins, and scaffold support.
• DOOMSCROLLR — last commit 2026-05-27, shares agent-tools
  Build owned-audience websites: pages, posts, products, subscribers, ShopMy/Shopify imports.
• MCP Queen — last commit 2026-07-29, shares agent-tools
  The evidence layer for MCP: live operational grades plus Trust Receipts for every registry server.
• PrintYourDuck Quote — last commit 2026-08-06, shares agent-tools
  Find and submit local 3D print files for manual PrintYourDuck quote review.
• Promptibus MCP — last commit 2026-05-11, shares agent-tools
  Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.

These share tags the maintainers applied themselves, such as deep-research, llm-cost, agent-tools. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: agent-tools, ai-agents, benchmarking, claude, compare-models, deep-research, llm, llm-cost, mcp, mcp-server, model-context-protocol, open-source-ai, pdf-translate.