Compare software and devices with dated, sourced facts; unknown values stay marked as unknown.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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.
The question in words, up to 300 characters.
Attribute keys of read requirements to set aside, e.g. ["ram_gb"]. They stay listed under requirements.removed and are not checked. Same as ?without= on the website.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http catalog https://sourcetier.com/mcp
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.
| Argument | Type | Description |
|---|---|---|
| without | array | Attribute keys of read requirements to set aside, e.g. ["ram_gb"]. They stay listed under requirements.removed and are not checked. Same as ?without= on the website. |
| question* | string | The question in words, up to 300 characters. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"question"
],
"properties": {
"without": {
"type": "array",
"items": {
"type": "string",
"maxLength": 60
},
"maxItems": 12,
"description": "Attribute keys of read requirements to set aside, e.g. [\"ram_gb\"]. They stay listed under requirements.removed and are not checked. Same as ?without= on the website."
},
"question": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "The question in words, up to 300 characters."
}
},
"additionalProperties": false
}Use this when the user wants to compare two to 5 named products from the catalog on their documented attributes. Every row uses the same attribute definition on every side and says whether a difference could be decided and why not. A cell with verification_state "unknown" is a gap in our research, never a missing feature. Do not use for products that are not in the catalog.
| Argument | Type | Description |
|---|---|---|
| slugs* | array | Two to five product slugs from search_products. |
| differences_only | boolean | Omit rows in which every product carries the same value. Undecided rows always stay. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slugs"
],
"properties": {
"slugs": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]*$",
"maxLength": 120,
"minLength": 1
},
"maxItems": 5,
"minItems": 2,
"description": "Two to five product slugs from search_products."
},
"differences_only": {
"type": "boolean",
"default": false,
"description": "Omit rows in which every product carries the same value. Undecided rows always stay."
}
},
"additionalProperties": false
}Use this when the user asks what else to consider instead of a named product. Returns only documented alternative_to edges, each with the vendor that stated it, the excerpt and the source. An empty list means we hold no documented alternative - it never means none exist; use search_products with the product's category for candidates.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The product slug. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]*$",
"maxLength": 120,
"minLength": 1,
"description": "The product slug."
}
},
"additionalProperties": false
}Use this before interpreting confidence numbers or verification states, or when the user asks how facts are verified: source tiers, the confidence formula, the publishing gate per page type and the measured precision of the readers. Everything is read from the code that applies it.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The product slug from search_products, e.g. "apple-macbook-air". |
| attributes | string | "all" returns every attribute including the unknown ones; "documented" omits the unknown ones and counts them instead. Use "documented" to save context when the gaps do not matter. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]*$",
"maxLength": 120,
"minLength": 1,
"description": "The product slug from search_products, e.g. \"apple-macbook-air\"."
},
"attributes": {
"enum": [
"documented",
"all"
],
"type": "string",
"default": "all",
"description": "\"all\" returns every attribute including the unknown ones; \"documented\" omits the unknown ones and counts them instead. Use \"documented\" to save context when the gaps do not matter."
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| slug | string | A product slug for its own timeline. Omit for the catalog-wide feed. |
| limit | integer | |
| since | string | Feed only: earliest day, YYYY-MM-DD. |
| types | array | Feed only: change types to include. Known: price_drop, price_increase, new_price, new_product, new_ai_agent, new_integration, new_alternative, security_certification, product_change, documented, research_update, funding, acquisition, source_changed. |
| category | string | Feed only: a category slug. |
| statement_id | string | Feed only: the stable statement id from a product attribute. Includes corrections and withdrawals. |
| include_minor | boolean | Include changes that are not material. |
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.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The product slug from search_products. |
| as_of* | string | YYYY-MM-DD or an ISO 8601 timestamp with a time zone. |
| attributes | string | "all" (default, same as the REST answer) returns every statement; "documented" omits the unknown ones and counts them in unknown_statements_omitted. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug",
"as_of"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]*$",
"maxLength": 120,
"minLength": 1,
"description": "The product slug from search_products."
},
"as_of": {
"type": "string",
"maxLength": 40,
"description": "YYYY-MM-DD or an ISO 8601 timestamp with a time zone."
},
"attributes": {
"enum": [
"documented",
"all"
],
"type": "string",
"default": "all",
"description": "\"all\" (default, same as the REST answer) returns every statement; \"documented\" omits the unknown ones and counts them in unknown_statements_omitted."
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| statement_id* | string | The statement_id from an attribute or scoped value of get_product, or from a change. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"statement_id"
],
"properties": {
"statement_id": {
"type": "string",
"pattern": "^st_[0-9a-f]{20}$",
"description": "The statement_id from an attribute or scoped value of get_product, or from a change."
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The vendor slug, e.g. "apple". |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]*$",
"maxLength": 120,
"minLength": 1,
"description": "The vendor slug, e.g. \"apple\"."
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many ranked products to return. |
| inputs | object | The profile's inputs by key, e.g. {"budget": 1200, "max_weight_kg": 1.4}. Out-of-range values are clamped and reported, not rejected. |
| profile | string | A finder profile key, e.g. "portable-laptop". Omit to get the list of profiles first. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1,
"description": "How many ranked products to return."
},
"inputs": {
"type": "object",
"description": "The profile's inputs by key, e.g. {\"budget\": 1200, \"max_weight_kg\": 1.4}. Out-of-range values are clamped and reported, not rejected.",
"additionalProperties": {
"type": [
"number",
"string",
"boolean"
]
}
},
"profile": {
"type": "string",
"maxLength": 80,
"description": "A finder profile key, e.g. \"portable-laptop\". Omit to get the list of profiles first."
}
},
"additionalProperties": false
}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".
| Argument | Type | Description |
|---|---|---|
| kind | string | Product kind, e.g. "software", "hardware", "ai_agent", "service". |
| limit | integer | |
| query | string | Words to search for: a product name, a category, a vendor, a need. Example: "MacBook Air". For a natural-language buying question, use ask_question. |
| vendor | string | Vendor slug, e.g. "apple". |
| filters | object | Attribute filters as on the website: {"soc2_type2": true}, {"ram_gb.min": 16}. Unknown attribute keys are reported back, never silently ignored. |
| category | string | Category slug, e.g. "crm". get categories from the categories resource. |
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 19, 2026.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]*$",
"maxLength": 120,
"minLength": 1,
"description": "A product slug for its own timeline. Omit for the catalog-wide feed."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Feed only: earliest day, YYYY-MM-DD."
},
"types": {
"type": "array",
"items": {
"enum": [
"price_drop",
"price_increase",
"new_price",
"new_product",
"new_ai_agent",
"new_integration",
"new_alternative",
"security_certification",
"product_change",
"documented",
"research_update",
"funding",
"acquisition",
"source_changed"
],
"type": "string"
},
"description": "Feed only: change types to include. Known: price_drop, price_increase, new_price, new_product, new_ai_agent, new_integration, new_alternative, security_certification, product_change, documented, research_update, funding, acquisition, source_changed."
},
"category": {
"type": "string",
"maxLength": 120,
"description": "Feed only: a category slug."
},
"statement_id": {
"type": "string",
"pattern": "^st_[0-9a-f]{20}$",
"description": "Feed only: the stable statement id from a product attribute. Includes corrections and withdrawals."
},
"include_minor": {
"type": "boolean",
"default": false,
"description": "Include changes that are not material."
}
},
"additionalProperties": false
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"kind": {
"type": "string",
"maxLength": 40,
"description": "Product kind, e.g. \"software\", \"hardware\", \"ai_agent\", \"service\"."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"default": "",
"maxLength": 300,
"description": "Words to search for: a product name, a category, a vendor, a need. Example: \"MacBook Air\". For a natural-language buying question, use ask_question."
},
"vendor": {
"type": "string",
"maxLength": 120,
"description": "Vendor slug, e.g. \"apple\"."
},
"filters": {
"type": "object",
"description": "Attribute filters as on the website: {\"soc2_type2\": true}, {\"ram_gb.min\": 16}. Unknown attribute keys are reported back, never silently ignored.",
"additionalProperties": {
"type": [
"string",
"number",
"boolean"
]
}
},
"category": {
"type": "string",
"maxLength": 120,
"description": "Category slug, e.g. \"crm\". get categories from the categories resource."
}
},
"additionalProperties": false
}