FutureSmart AI Demos

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Search evidence-backed AI-tool reviews, rankings, use cases, comparisons & toolkits (read-only).

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "FutureSmart AI Demos": {
      "url": "https://mcp.aidemos.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (17)

• answer

  ANSWER a buyer question in ONE call: which tool is best at a specific capability, with proof. Returns the resolved verdict our testing team's evidence supports — a named winner FOR THE ASKED CRITERION, every tested tool ranked with a comparable score /5, the CONDITIONS each result holds under (e.g. 'clean tables yes; nested headers no'), dissenting observations preserved as openable links, the tie-break reason, and artifact proof URLs. Answers are materialized from the evidence substrate — the same question returns the same answer. Honestly refuses (coverage: not_tested) when we never tested the topic. Start HERE for any 'which tool is best at X' / 'A or B for X' question; use get_evidence for the raw cells behind it.

  Parameters:

  • ranking — string — Ranking slug (skips routing).
  • question — string — The buyer question in natural language, e.g. 'Which document extraction tool best preserves table structure from scanned PDFs?'. Alternative: pass ranking + criterion explicitly.
  • scenario — string — Optional scenario/condition of interest.
  • criterion — string — Criterion slug or exact name (with `ranking`).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_use_cases

  List published use-case pages (how-to guides): id, title, slug, url, persona, category, updated_at.

  Parameters:

  • limit — integer — Max items to return. Omit for all.
  • offset — integer — Items to skip (paging).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_rankings

  List published ranking pages ("best X"): id, title, slug, url, use_case, persona, category, tools_count, winner, tested_as_of, updated_at.

  Parameters:

  • limit — integer — Max items to return. Omit for all.
  • offset — integer — Items to skip (paging).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_tools

  List published AI tool pages: id, name, slug, url, domain, personas[], categories[].

  Parameters:

  • limit — integer — Max items to return. Omit for all.
  • offset — integer — Items to skip (paging).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_compares

  List published head-to-head comparison pages: id, title, slug, url, tool_a, tool_b, personas[], shared_use_cases[], updated_at.

  Parameters:

  • limit — integer — Max items to return. Omit for all.
  • offset — integer — Items to skip (paging).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_toolkits

  List published toolkit pages (curated bundles): id, title, slug, url, category.

  Parameters:

  • limit — integer — Max items to return. Omit for all.
  • offset — integer — Items to skip (paging).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_personas

  List personas with published-page counts per type {use_cases, rankings, tools, compares, toolkits}. The slugs are valid input for get_persona.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_categories

  List the category vocabulary in use with per-type counts and a source flag ("collection"|"derived"), sorted by total.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• search

  Search the published catalogue across use cases, rankings, tools, comparisons, and toolkits. Returns ranked light refs [{ kind, id, title, slug, url, snippet, score, meta }] — then call get_tool / get_ranking / get_use_case for full detail. `mode`: keyword (substring), semantic (meaning, via embeddings — finds pages by what they cover), or hybrid (default, fuses both). Optional filters: type[], persona, category.

  Parameters:

  • query (required) — string — Free-text search query.
  • mode — string — Search mode.
  • type — array — Restrict to these kinds (default: all).
  • limit — integer — Max results (default 20).
  • persona — string — Restrict to items tagged with this persona slug.
  • category — string — Restrict to this category (case-insensitive).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• tools_in_ranking

  Given a ranking id, return the ranking {id,title,slug} and its ranked tools [{id,name,slug,url,rank,badge}] (badge: Best/Usable/Needs work/Unstable/Failed).

  Parameters:

  • ranking_id (required) — ['string', 'integer'] — Ranking id (from list_rankings).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• rankings_for_tool

  Given a tool id, return the tool {id,name,slug} and every ranking it appears in [{id,title,slug,url,use_case,rank,badge}].

  Parameters:

  • tool_id (required) — ['string', 'integer'] — Tool id (from list_tools).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_persona

  Given a persona slug (from list_personas), return everything tagged with it: persona, use_cases[], rankings[], compares[], toolkits[], tools[]. Mirrors a persona landing page.

  Parameters:

  • slug (required) — string — Persona slug, e.g. "students".

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_tool

  Full tool detail as a JSON+Markdown envelope: identity, pricing, per-feature scores, fit, FAQ, relationships (JSON) + our_take / in-depth review (Markdown). Includes `proof`: real artifact URLs (input/output screenshots, recordings) from the runs that tested it, each with the /evidence permalink for the finding it proves — you can cite evidence from THIS call. null if unknown. Pass `fields` to project to only the keys you need (token-efficient).

  Parameters:

  • slug (required) — string — Tool seo_slug, e.g. "affinda" (from list_tools).
  • proof — string — How many proof artifacts to inline. "sample" (default) = up to 6 per tool, spread across distinct criteria so you see breadth; "full" = every artifact; "none" = counts only, no URLs. Counts (artifact_count / finding_count) are the TRUE totals in every mode, so you can always tell what you did not receive.
  • fields — array — Optional projection: return ONLY these top-level fields (identity id/name/title/slug/url is always included) to control response size. Available: id, name, slug, url, heading, website, domain, category, sub_category, content_type, personas, tags, rating, testing_history, features, pricing, fit, use_case_track_record, related_pages, related_reads, similar_tools, faq, demo_video, our_take, in_depth_review_md, proof.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_ranking

  Full ranking detail as a JSON+Markdown envelope: ranked tools (rank/badge/scores), criteria, winner, breakdown (JSON) + verdicts / final take (Markdown). Every ranked tool carries `proof`: real artifact URLs from the exact evidence run this page is bound to, each with the /evidence permalink for the finding it proves — verdict and proof arrive together, no second call needed to cite evidence. `proof.artifact_count` is the true total and `proof.all_findings` is the get_evidence call that returns all of it. null if unknown. Pass `fields` to project to only the keys you need (token-efficient).

  Parameters:

  • slug (required) — string — Ranking slug, e.g. "resume-parsing-api" (from list_rankings).
  • proof — string — How many proof artifacts to inline. "sample" (default) = up to 6 per tool, spread across distinct criteria so you see breadth; "full" = every artifact; "none" = counts only, no URLs. Counts (artifact_count / finding_count) are the TRUE totals in every mode, so you can always tell what you did not receive.
  • fields — array — Optional projection: return ONLY these top-level fields (identity id/name/title/slug/url is always included) to control response size. Available: id, title, slug, url, abstract, read_time, tested_date, category, use_case, personas, tags, winner, methodology, tools, breakdown, final_take, evidence_run.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_use_case

  Full use-case detail as a JSON+Markdown envelope: step guide, pros/cons, FAQ, tools used (JSON) + the full narrative guide (Markdown, full_md). null if unknown. Pass `fields` to project to only the keys you need (token-efficient).

  Parameters:

  • slug (required) — string — Use-case slug (from list_use_cases).
  • fields — array — Optional projection: return ONLY these top-level fields (identity id/name/title/slug/url is always included) to control response size. Available: id, title, slug, url, abstract, read_time, category, audience, personas, tags, tools_used, step_guide, what_to_expect, faq, full_md.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_evidence

  Query the evidence graph: observation cells (tool × test-scenario × criterion) → verdict, score, the researcher's note, and the REAL artifacts (input/output screenshots) that prove it. The ground truth behind every ranking — filter any combination of tool(s), scenario (slug, group tag, or name), criterion, verdict, or evidence state. evidence_state: "verified" = artifact-backed, "observed" = noted without artifact, "scored-only" = number only.

  Parameters:

  • tool — string — Tool slug or name, e.g. "landing-ai".
  • limit — integer — Max cells (default 50).
  • tools — array — Several tools at once.
  • ranking — string — Ranking page slug — scope cells to the evidence run that published ranking is bound to (exactly what the page renders).
  • verdict — string
  • evidence — string
  • scenario — string — Scenario slug, cross-run group tag (e.g. "scanned-research-paper"), or name fragment.
  • criterion — string — Criterion slug or name, e.g. "table extraction".

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compare_tools

  Evidence-aligned comparison of two tools, honesty enforced structurally: head_to_head (cells from the SAME test input — provable same-input comparison), related_not_same_input (same dimension, different runs — flagged), and each tool's unique evidence. Built from real observation cells with artifacts, not prose.

  Parameters:

  • tool_a (required) — string — First tool slug, e.g. "llamaparse".
  • tool_b (required) — string — Second tool slug, e.g. "landing-ai".
  • criterion — string — Optional: restrict to one criterion.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.