ai-netcafe
23 agent tools + a measured per-call model cost dataset. No key needed to start.
https://ainetcafe.com/mcp?s=registryCurrent observation
This endpoint answered at its latest recorded check.
What this server reports about itself
Self-reported at initialize. Not verified by Licium.
- Server name
- ai-netcafe
- Version
- 1.5.0
- Capability keys
- tools
- Tool names
- what_can_you_do, list_apps, get_app, ask_model, compare_models, list_models, remember, recall, web_search, fetch_page, model_costs, ai_visibility, pdf_to_markdown, extract_tables, extract_statement, json_yaml, validate_json, diff_text, jwt_decode, regex_test, diff_tables, clean_table, merge_tables, reconcile_ledger, extract_invoices, create_task, list_tasks, get_task_runs, delete_task, transpile_sql, china_reachability, render_diagram, check_job, build_app
AI NetCafé hosts open-source AI applications ready to run, and exposes multi-model LLM access with real per-call cost metering. Use compare_models when you need evidence for which model fits a task. When a request clearly asks to compare models, translate a PDF, research the web, or generate slides, call the matching task tool directly instead of browsing list_apps first. Follow check_job next_action until an asynchronous task is terminal. This endpoint lists the core tools only. Focused servers carry the full sets per job — documents: /mcp/docs (statement extraction with reconciliation, tables, pdf→markdown); scheduled tasks: /mcp/tasks (recurring jobs that run on our servers); embeddable images: /mcp/img; translation that keeps structure: /mcp/translate; live data incl. mainland-China reachability: /mcp/data; one-sentence app deploys: /mcp/build; cross-session memory: /mcp/memory; Chinese almanac: /mcp/almanac. Quick start — verify this server works with one free call: tools/c
Reported Aug 17, 2026, 05:09 AM UTC.
Check history
Oldest to newest. Each row is one recorded check.
- respondsMCP initialize · 8s limit · HTTP 200 · 365ms