com.ainetcafe/ai-netcafe

Est-ce que com.ainetcafe/ai-netcafe est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.ainetcafe/ai-netcafe » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 34 outils

• ai_visibility≈ 186 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Page to audit, e.g. https://example.com

  Exemple d'appel

  {"name": "ai_visibility", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ask_model≈ 267 tokens

  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); capacity limits still apply. Example — GET https://ainetcafe.com/t/ask_model?prompt=Say+hi&model=deepseek-v4-flash

  Paramètres, retour & exemple (4)

  Paramètres

  • model · string · optionnel
    Model id. Call list_models for available ids. Defaults to a cheap capable model.
  • prompt · string · requis
    The prompt to send.
  • system · string · optionnel
    Optional system instruction.
  • max_tokens · integer · optionnel
    Optional output cap.

  Exemple d'appel

  {"name": "ask_model", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"model": "texte", "answer": "texte", "cost_usd": 1, "latency_ms": 1}}

• build_app≈ 330 tokens

  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

  Paramètres, retour & exemple (4)

  Paramètres

  • name · string · optionnel
    Optional short app name (defaults to the description).
  • refine · string · optionnel
    Slug of an app you built earlier (e.g. "u-1a23e679") to modify instead of building from scratch — describe only the change in `description`.
  • visibility · string · optionnel
    "public" (default, listed in the store) or "unlisted" (URL-only, not in the store).
  • description · string · requis
    What the tool should do, in any language. Be specific about inputs/outputs.

  Exemple d'appel

  {"name": "build_app", "arguments": {"description": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_job≈ 270 tokens

  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>

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis
    The job_id returned when the task was started.

  Exemple d'appel

  {"name": "check_job", "arguments": {"job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"kind": "texte", "error": "texte", "job_id": "texte", "result": "texte", "status": "texte", "is_terminal": true, "next_action": {}, "structured_result": "texte", "retry_after_seconds": 1}}

• china_reachability≈ 171 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Full URL to test, e.g. https://example.com

  Exemple d'appel

  {"name": "china_reachability", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• clean_table≈ 448 tokens

  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 cell can say "empty" (NA / null / - / 无), drops empty rows and columns, and can split one column into several. Returns the cleaned CSV plus exactly what changed: rows in, rows out, duplicates removed, cells trimmed per column. It can also transpose rows/columns and unpivot a wide table into a long one. The row arithmetic is verified in code — if in − removed ≠ out, the response says so instead of handing back a table nobody can check. Use when a CSV came out of Excel or an export and needs cleaning before analysis.

  Paramètres, retour & exemple (6)

  Paramètres

  • ops · string · optionnel
    Comma-separated, default "dedupe,trim,drop_empty,unify_blank". Also available: split_column, transpose (swap rows/columns), wide_to_long (unpivot a wide table into the long format analysis tools expect).
  • url · string · optionnel
    Link to the CSV. Provide this or text.
  • keep · string · optionnel
    For wide_to_long: comma-separated id columns to keep as-is. Defaults to the first column.
  • text · string · optionnel
    The CSV content itself. Provide this or url.
  • split_by · string · optionnel
    Separator to split on, default a single space.
  • split_column · string · optionnel
    Column name to split (requires ops to include split_column).

  Exemple d'appel

  {"name": "clean_table", "arguments": {"ops": "texte", "url": "texte", "keep": "texte", "text": "texte", "split_by": "texte", "split_column": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• compare_models≈ 293 tokens

  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 the user charge ($0.00). This answers "which model should I actually use for this kind of task?" with data instead of guesswork. Example — GET https://ainetcafe.com/t/compare_models?prompt=Explain+CAP+theorem+in+1+line

  Paramètres, retour & exemple (3)

  Paramètres

  • models · array · optionnel
    Model ids to compare (2-5). Defaults to a cheap/mid/strong spread.
  • prompt · string · requis
    The prompt to send to every model.
  • system · string · optionnel
    Optional system instruction applied to all.

  Exemple d'appel

  {"name": "compare_models", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": [], "summary": {}}}

• create_task≈ 376 tokens

  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); pipeline (Run one of your production lines (create_pipeline) on a schedule; every run leaves a proof-carrying work order). Needs a workspace token (?w=ws_... on your MCP URL) so you can manage it later. Application and model calls are subsidized during the free beta; your charge is $0.00 and capacity limits apply.

  Paramètres, retour & exemple (4)

  Paramètres

  • kind · string · requis
    watch_page | daily_answer | watch_reachability | pipeline
  • input · string · requis
    The URL to watch, or the question to re-research.
  • notify_url · string · optionnel
    Optional https webhook to POST results to when they change.
  • interval_seconds · integer · optionnel
    How often to run. Minimum 900 (15 min), default 3600.

  Exemple d'appel

  {"name": "create_task", "arguments": {"kind": "texte", "input": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• delete_task≈ 113 tokens

  Stop and remove a scheduled task and its run history.

  Paramètres, retour & exemple (1)

  Paramètres

  • task_id · integer · requis
    From list_tasks.

  Exemple d'appel

  {"name": "delete_task", "arguments": {"task_id": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• diff_tables≈ 280 tokens

  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 the exact column and both values. Unlike reconcile_ledger this needs no amount column, so it also fits name lists, inventory counts, permission tables, and any "these two exports should match" check.

  Paramètres, retour & exemple (5)

  Paramètres

  • key · string · requis
    Column that identifies a row, e.g. id.
  • url_a · string · optionnel
    Link to the first CSV.
  • url_b · string · optionnel
    Link to the second CSV.
  • text_a · string · optionnel
    Or the first CSV content directly.
  • text_b · string · optionnel
    Or the second CSV content directly.

  Exemple d'appel

  {"name": "diff_tables", "arguments": {"key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• diff_text≈ 194 tokens

  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 two versions of a config, a document, or any command output, instead of asking an LLM to eyeball two blobs and hoping it notices.

  Paramètres, retour & exemple (2)

  Paramètres

  • a · string · requis
    The first (before) text.
  • b · string · requis
    The second (after) text.

  Exemple d'appel

  {"name": "diff_text", "arguments": {"a": "texte", "b": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• extract_invoices≈ 249 tokens

  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 checked in code — net + tax must equal gross — and the batch total is re-added independently, so a row the model misread is flagged with the exact difference instead of quietly landing in your books. Mixed currencies get no batch total on purpose: adding them together would be an accounting error. CSV is UTF-8 with BOM so Excel opens it right.

  Paramètres, retour & exemple (1)

  Paramètres

  • urls · string · requis
    Invoice URLs — comma-separated, or pass an array. Up to 20 per call.

  Exemple d'appel

  {"name": "extract_invoices", "arguments": {"urls": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• extract_statement≈ 210 tokens

  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).

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Public URL of the statement PDF.

  Exemple d'appel

  {"name": "extract_statement", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• extract_tables≈ 221 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    Public URL of the PDF.
  • fields · string · optionnel
    Optional comma-separated target columns, e.g. "invoice_no,supplier,date,amount". Omit to infer from the header.

  Exemple d'appel

  {"name": "extract_tables", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• fetch_page≈ 198 tokens

  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 pages, use web_search, a browser, or the site's API. Use it after web_search to read a reachable public source, or to ingest a static page for analysis. Example — GET https://ainetcafe.com/t/fetch_page?url=https://example.com

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    The page URL to fetch.

  Exemple d'appel

  {"name": "fetch_page", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_app≈ 186 tokens

  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>

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Application slug, from list_apps.

  Exemple d'appel

  {"name": "get_app", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "slug": "texte", "open_url": "texte"}}

• get_task_runs≈ 165 tokens

  Recent runs of one scheduled task: what it returned, whether the result changed, and measured platform cost metadata. User charge is $0.00.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    How many recent runs, max 20, default 5.
  • task_id · integer · requis
    From create_task or list_tasks.

  Exemple d'appel

  {"name": "get_task_runs", "arguments": {"task_id": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• json_yaml≈ 207 tokens

  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 of silently producing something that looks fine and is not. Use when a config, a CI file, or a Kubernetes manifest needs to be in the other format.

  Paramètres, retour & exemple (2)

  Paramètres

  • to · string · optionnel
    Optional: "json" or "yaml" to force the direction.
  • text · string · requis
    The JSON or YAML content.

  Exemple d'appel

  {"name": "json_yaml", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• jwt_decode≈ 194 tokens

  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 response says so — decoding is fine for debugging a token you already hold, but never treat these values as proof of anything; verification needs the secret and belongs in your own service.

  Paramètres, retour & exemple (1)

  Paramètres

  • token · string · requis
    The JWT string.

  Exemple d'appel

  {"name": "jwt_decode", "arguments": {"token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_apps≈ 280 tokens

  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

  Paramètres, retour & exemple (1)

  Paramètres

  • category · string · optionnel
    Optional filter, e.g. "office", "research", "chat".

  Exemple d'appel

  {"name": "list_apps", "arguments": {"category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"apps": [], "try_in_browser": "texte"}}

• list_models≈ 205 tokens

  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 user charge is $0.00 during the beta. Example — GET https://ainetcafe.com/t/list_models

  Paramètres, retour & exemple (1)

  Paramètres

  • tier · string · optionnel · free | premium
    Optional reference tier filter. All currently healthy tiers are available without a user key during the beta.

  Exemple d'appel

  {"name": "list_models", "arguments": {"tier": "free"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"models": []}}

• list_tasks≈ 113 tokens

  Show scheduled tasks, next run times, run counts, and measured platform cost metadata. User charge is $0.00 during the beta.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_tasks", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• merge_tables≈ 248 tokens

  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 never shift silently — the failure mode that makes hand-merged spreadsheets untrustworthy. Reports each source file row count and checks in code that they sum to the merged total. Use for monthly exports, per-store sheets, or any set of files with the same subject but drifting headers.

  Paramètres, retour & exemple (2)

  Paramètres

  • urls · string · optionnel
    Comma-separated CSV links, at least two.
  • texts · array · optionnel
    Or pass the CSV contents directly as an array.

  Exemple d'appel

  {"name": "merge_tables", "arguments": {"urls": "texte", "texts": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• model_costs≈ 247 tokens

  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'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

  Paramètres, retour & exemple (1)

  Paramètres

  • days · integer · optionnel
    Measurement window in days (default 30).

  Exemple d'appel

  {"name": "model_costs", "arguments": {"days": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• pdf_to_markdown≈ 178 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Public URL of the PDF, or of a page image (png/jpg) for scanned documents.

  Exemple d'appel

  {"name": "pdf_to_markdown", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• recall≈ 219 tokens

  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)

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Max results (default 8, up to 20).
  • query · string · optionnel
    Optional search terms; omit to list the most recent.
  • project · string · optionnel
    Optional project filter.

  Exemple d'appel

  {"name": "recall", "arguments": {"limit": 1, "query": "texte", "project": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• reconcile_ledger≈ 401 tokens

  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 returns three lists: only in A, only in B, and same key but different amount. Amounts are compared in integer cents, so 0.1 + 0.2 never invents a phantom difference for someone to chase. The response also proves the result: the listed differences are re-added and must equal the gap between the two totals, checked in code. Use for month-end close, platform payouts vs orders, or any "these two numbers should agree and do not" problem. This is the job people do by hand with VLOOKUP or a groupby and then cannot prove they got right.

  Paramètres, retour & exemple (6)

  Paramètres

  • key · string · requis
    Column name to match rows on, e.g. order_id.
  • url_a · string · optionnel
    Link to side A (e.g. your books).
  • url_b · string · optionnel
    Link to side B (e.g. the statement).
  • amount · string · requis
    Numeric column to compare, e.g. amount.
  • text_a · string · optionnel
    Or the CSV content of side A directly.
  • text_b · string · optionnel
    Or the CSV content of side B directly.

  Exemple d'appel

  {"name": "reconcile_ledger", "arguments": {"key": "texte", "amount": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• regex_test≈ 222 tokens

  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 into code, instead of guessing whether the escaping survived the trip through JSON and the shell.

  Paramètres, retour & exemple (3)

  Paramètres

  • text · string · requis
    The text to test against.
  • flags · string · optionnel
    Optional flags, e.g. "gi". Default "g".
  • pattern · string · requis
    The regular expression, without surrounding slashes.

  Exemple d'appel

  {"name": "regex_test", "arguments": {"text": "texte", "pattern": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• remember≈ 260 tokens

  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 per-caller/workspace memory pool; no personal API key is required. Do not store secrets or raw logs. Example — tools/call remember {"content":"Deploy key rotates monthly"}

  Paramètres, retour & exemple (3)

  Paramètres

  • kind · string · optionnel · decision | preference | bugfix | discovery | note
    Category; default "note".
  • content · string · requis
    The memory itself, self-contained (≤2000 chars).
  • project · string · optionnel
    Optional project name to scope recall later.

  Exemple d'appel

  {"name": "remember", "arguments": {"content": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• render_diagram≈ 235 tokens

  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"

  Paramètres, retour & exemple (3)

  Paramètres

  • type · string · optionnel
    Diagram language: mermaid (default), plantuml, graphviz, c4plantuml, excalidraw, blockdiag, erd…
  • format · string · optionnel
    "svg" (default) or "png".
  • source · string · requis
    The diagram source code (e.g. a Mermaid flowchart).

  Exemple d'appel

  {"name": "render_diagram", "arguments": {"source": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• transpile_sql≈ 280 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • sql · string · requis
    The SQL statement (or several, separated by semicolons).
  • read · string · optionnel
    Source dialect, e.g. "mysql". Omit to auto-detect from generic SQL.
  • write · string · requis
    Target dialect, e.g. "postgres", "bigquery", "doris".

  Exemple d'appel

  {"name": "transpile_sql", "arguments": {"sql": "texte", "write": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• validate_json≈ 223 tokens

  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/false. Checks required + types only — not full JSON Schema, and it says so rather than pretending. Use before feeding generated JSON into something that will fail on it.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    The JSON to validate.
  • schema · string · optionnel
    Optional JSON Schema (as JSON text) — required[] and properties[].type are checked.

  Exemple d'appel

  {"name": "validate_json", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• web_search≈ 188 tokens

  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

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · requis
    The search query.
  • max_results · integer · optionnel
    Max results (default 8, up to 20).

  Exemple d'appel

  {"name": "web_search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• what_can_you_do≈ 248 tokens

  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 whole catalogue and guessing. Also returns multi-step recipes when a task needs several tools chained (invoices to a ledger, a bank statement reconciled, a messy CSV turned into a deliverable). Deterministic and free: it calls no model, costs nothing, and never runs out of quota. Call this FIRST when you are not sure what this server offers.

  Paramètres, retour & exemple (1)

  Paramètres

  • task · string · requis
    What you are trying to do, e.g. "reconcile a bank statement against my books" or "把一堆发票整理成能入账的表格"

  Exemple d'appel

  {"name": "what_can_you_do", "arguments": {"task": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

ai-netcafe@1.2.1