SourceTier
Server Details
Compare software and devices with dated, sourced facts; unknown values stay marked as unknown.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
The family of product-data tools (get_product, get_product_record, get_product_changes, get_statement) shares a subject but each targets a distinct axis: current profile, record as-of a date, change timeline, and per-statement version history, and the descriptions spell these out. The one real soft spot is ask_question vs search_products vs recommend_products, all of which start from a user need; the descriptions do draw the line (plain-language buying question, attribute filter query, ranked shortlist) but an agent could still hesitate between them.
Every name is a predictable snake_case verb_noun pair drawn from a small verb set (get_, search_, compare_, recommend_, ask_). The get_* family is further disciplined with noun modifiers (get_product, get_product_changes, get_product_record), which reads as one deliberate scheme rather than mixed conventions.
Eleven tools sit squarely in the well-scoped 3-15 range for a sourced product-catalog server. Each one covers a distinct query shape (search, retrieve, compare, historical, provenance, methodology) and no tool looks like a redundant wrapper.
The surface covers discovery (search, ask, recommend), depth (get_product, compare, vendor), provenance (methodology, get_statement) and time (changes, record) — an unusually complete lifecycle for evidence-backed product research. The notable gap is price: the description explicitly routes prices to a separate /api/v1/products/{slug}/prices endpoint, so a price_drop change type exists but no tool can read current or historical prices directly, and there is no browse/list-categories tool.
Available Tools
11 toolsask_questionAsk a question in wordsARead-onlyIdempotentInspect
Use this for a buying question in plain words ("laptop under 1.5 kg with 16 GB RAM", "CRM with SOC 2 and EU data residency"). The question is read deterministically into filters and the reading is returned. It is the SAME evaluation as the website and /api/v1/ask. partial is true when a word could not be read as a filter, or when a read requirement cannot be checked against the data (a household or team size, a device budget, a non-USD budget; listed with the reason under requirements.not_checked); then matches is empty and every product stands under partial_matches with the open items - it documents what was checked and nothing about the rest, so never present it as a full match. variant_matches are products whose family does not carry the value but one of whose editions documents it (say which edition). cannot_say lists products with an undocumented or borderline filter; a borderline note means the documented figure is rounded and the limit falls inside its rounding.
Inputs: question (required), without. Returns: read, matches, partial, web_url, +9 more
compare_productsCompare productsARead-onlyIdempotentInspect
Use this when the user wants to compare two to 5 named products from the catalog on their documented attributes. Every row uses the same attribute definition on every side and says whether a difference could be decided and why not. A cell with verification_state "unknown" is a gap in our research, never a missing feature. Do not use for products that are not in the catalog.
Inputs: slugs (required), differences_only. Returns: rows, web_url, contract, products, +3 more
get_alternativesDocumented alternatives to a productARead-onlyIdempotentInspect
Use this when the user asks what else to consider instead of a named product. Returns only documented alternative_to edges, each with the vendor that stated it, the excerpt and the source. An empty list means we hold no documented alternative - it never means none exist; use search_products with the product's category for candidates.
Inputs: slug (required). Returns: url, name, slug, count, +2 more
get_methodologyHow the evidence worksARead-onlyIdempotentInspect
Use this before interpreting confidence numbers or verification states, or when the user asks how facts are verified: source tiers, the confidence formula, the publishing gate per page type and the measured precision of the readers. Everything is read from the code that applies it.
Inputs: no named parameters. Returns: web_url, source_tiers, confidence_cap, index_threshold, +3 more
get_productRead a product with evidenceARead-onlyIdempotentInspect
Use this to answer "does product X have/support Y" and for the full profile of one product: every documented attribute with verification_state, confidence, observed_on and source URLs; scoped values (one edition, region or package only), withdrawn statements, register identifiers and the vendor mark. Needs the slug from search_products. Prices are at /api/v1/products/{slug}/prices. An attribute with verification_state "unknown" was searched and not found - say so, and never report it as the product lacking the feature.
Inputs: slug (required), attributes. Returns: url, kind, name, slug, +9 more
get_product_changesChanges to products and pricesARead-onlyIdempotentInspect
Use this for what changed: with a slug, the timeline of one product; without, the feed across the catalog since a date, filtered by change type (price_drop, new_integration, ...) or category. A research_update is a change to OUR knowledge (unknown, estimated), never to the product.
Inputs: slug, limit, since, types, +3 more. Returns: slug, count, since, types, +3 more
get_product_recordA product as recorded on a dateARead-onlyIdempotentInspect
Use this to reproduce what was known about a product at an earlier moment, e.g. when a decision was made: every statement our record held at as_of (a date means the end of that day, Europe/Berlin time), with its statement_id, value, verification_state, confidence_recorded and the sources retrieved by then. It is our record, not the page as it was served; before first_recorded_at nothing is claimed.
Inputs: slug (required), as_of (required), attributes. Returns: slug, as_of, count, contract, +3 more
get_statementThe history of one statementARead-onlyIdempotentInspect
Use this when you cite a value and need to know whether it changed, was corrected or withdrawn, or to re-check a value you stored earlier. Every attribute from get_product carries a statement_id that stays the same across new values, withdrawals and merges; this returns every version oldest first (value, verification_state, confidence_recorded, recorded_at, ended_by superseded/withdrawn with the reason, sources) and the changes attached to it, each marked if it was corrected.
Inputs: statement_id (required). Returns: changes, contract, page_url, versions, +3 more
get_vendorRead a vendor with evidenceARead-onlyIdempotentInspect
Use this for any question about the company behind a product (who makes it, where it is headquartered, when it was founded, which certifications and register entries it holds) instead of answering from memory: documented attributes with verification state and sources, the vendor's products, and register identifiers (LEI, SEC CIK, Wikidata) it can be checked against. Needs the vendor slug from search_products or from a product's vendor field.
Inputs: slug (required). Returns: url, kind, name, slug, +4 more
recommend_productsRank products against requirementsARead-onlyIdempotentInspect
Use this when the user states requirements (budget, weight, must-have features) and wants a ranked shortlist. Without a profile it lists the published finder profiles and their inputs; with a profile it ranks products with published weights, showing every contribution with its evidence. A criterion we could not measure never counts against a product: such products appear under not_enough_data, and only a documented failure rules a product out. For a free-text question use search_products instead.
Inputs: limit, inputs, profile. Returns: inputs, ranked, clamped, profile, +9 more
search_productsSearch productsARead-onlyIdempotentInspect
Use this FIRST, before answering from memory, whenever a question names or implies a technology product, vendor, category or need (does X support Y, who makes X, which tools have Z): the catalog holds dated, sourced evidence that memory does not. Full-text query plus optional filters on documented attributes (e.g. {"soc2_type2": "true", "ram_gb.min": "16"}). Returns matches (every filter documented) and cannot_say (a filter not documented - a research gap, never a no), with slugs for get_product, get_vendor and compare_products. An empty result means "not covered", not "does not exist".
Inputs: kind, limit, query, vendor, +2 more. Returns: query, matches, web_url, contract, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search and compare public hosting-provider facts with sources and explicit unknowns.
Compare published AI solution rankings, company facts and research benchmarks with sources.
Dated, sourced facts about AI and tech companies: what was true on a day, and what changed since.
Neutral, sourced comparisons on any topic, in 32 languages. Each value links to its source.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceSourced product prices, dated price history, specs and independent-test coverage across 4,764 hardware products and 2,064 software vendors — every figure returned with its source URL and the date it was captured. Unknown values come back as null rather than a guess, so an agent can cite what it surfaces.-

modelrefs-mcpofficial
AlicenseNot gradedqualityCmaintenanceGives agents inside the editor governed benchmark evidence with citations and methodology limitations, plus provider-documented retirement dates resolved for the exact snapshot a codebase pins. Comparisons across models are limited to runs sharing benchmark, metric and task subset, with everything incomparable listed and explained instead of ranked.504 npmMIT- AlicenseAqualityBmaintenanceVerified, dated facts for AI coding agents: what breaks between npm package versions (diffed from TypeScript types), per-version vulnerabilities, the newest version compatible with a given Node/Python/Rust/PHP, end-of-life dates of ~480 runtimes and frameworks, and AI model prices. Covers npm, PyPI, crates.io and Packagist.121AGPL 3.0
- AlicenseAqualityCmaintenanceEnables AI assistants to search and retrieve verified software comparisons, including current pricing with source and date, and ranked alternatives for software switching decisions.310 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.