SAGE Infinite Search

Server Details

Find fresh, source-backed rare and one-of-one products at independent retailers.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.

Status: Healthy
Uptime: 99.5% over 41 days
Last Tested: 2026-09-27 22:01
Transport: Streamable HTTP · MCP 2025-11-25
URL

TDQS

A4.1/5.0

Scored 2026-07-28 11:05 across 2 tools

Disambiguation5/5

The two tools, 'search' and 'fetch', have clearly distinct purposes: one retrieves a list of results based on a query, the other gets details for a specific result ID. No overlap or ambiguity.

Naming Consistency4/5

Both tool names are single imperative verbs ('search', 'fetch'), which is consistent in style. While not following a standard verb_noun pattern, they are uniform and clear.

Tool Count4/5

With only two tools, the server is very focused. This is appropriate for a specialized search service, though a few more tools (e.g., for filtering or pagination) might improve utility.

Completeness3/5

Essential operations are covered: querying and fetching details. However, missing features like filtering, sorting, or pagination could limit the agent's ability to handle non-trivial searches effectively.

Available Tools

2 tools

fetchA

Read-only

Inspect

Fetch one exact result id returned by this public-network search. SAGE rechecks the indexed retailer evidence before returning its source, URL, price, freshness, availability evidence, and limits. Read-only; never use an id not returned by search.

ParametersJSON Schema

Name	Required	Description	Default
`id`	Yes	Opaque result id returned by the SAGE search tool.

Output Schema

ParametersJSON Schema

Name	Required	Description
`id`	Yes
`url`	Yes
`text`	Yes
`title`	Yes
`metadata`	No

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint. Description adds that SAGE rechecks evidence before returning, listing specific data fields. No contradictions. Adds value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences front-loading the purpose and key constraints. No extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With output schema present and annotations covering safety, the description sufficiently explains behavior, usage context, and constraints. Complete for a single-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and description essentially repeats the schema's description of 'id' parameter. No additional semantics provided beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool fetches one exact result id from a public-network search, listing specific returned data (source, URL, price, etc.). Distinguishes from sibling tool 'search' by specifying it uses an id returned by search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says read-only and warns 'never use an id not returned by search', guiding appropriate usage after search. Could explicitly mention alternatives but context makes it clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

searchA

Read-only

Inspect

Search SAGE-connected stores and SAGE's verified public independent-retailer inventory network for a specific rare, vintage, discontinued, one-of-one, local, secondhand, or hard-to-find general-audience physical product. Results require fresh positive source evidence, a crawlable SAGE item page, and the underlying exact retailer source when fetched. When results is empty, show recovery.markdownLink to the shopper. Read-only: this tool cannot reserve, purchase, contact a retailer, or change inventory.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	The shopper's product request, including useful traits and location words they supplied.

Output Schema

ParametersJSON Schema

Name	Required	Description
`results`	Yes
`recovery`	No

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description reinforces the read-only nature and adds context about result requirements and empty result behavior. No contradictions. It adds value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately concise but front-loaded with the most important information. Each sentence serves a purpose: what it searches, requirements, error handling, and limitations. Could be slightly trimmed but remains efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (1 parameter, output schema exists, annotations present), the description covers the essential aspects: purpose, constraints, and behavior. It is sufficiently complete for an AI agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description for the single 'query' parameter is clear (100% coverage). The tool description does not add significant additional meaning for the parameter; it repeats the types of products. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches SAGE's store and inventory network for specific hard-to-find products. It uses a specific verb ('Search') and resource ('stores and inventory network'), and the scope is well-defined (rare, vintage, discontinued, etc.). This distinguishes it from the sibling 'fetch' tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description outlines conditions for use: results require fresh evidence, a crawlable page, and retailer source. It also specifies what the tool cannot do (reserve, purchase, etc.) and provides guidance for empty results. However, it does not explicitly compare with sibling tools like 'fetch'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

5 tool updatesJul 27, 2026
- Removedfind_inventory_alternatives
- Removedget_public_inventory_item
- Removedget_public_store_inventory
- Removedrequest_shopper_consent
- Removedsearch_local_inventory

5 tool updatesJul 19, 2026

Changedfind_inventory_alternatives2 fields changed

addedOutput schema / properties

Added value: +{
+  "nearby": {
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "ok": {
+    "type": "boolean"
+  },
+  "sameShop": {
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "sourceItem": {
+    "additionalProperties": true,
+    "type": "object"
+  }
+}

addedOutput schema / required

Added value: +[
+  "ok",
+  "sourceItem",
+  "sameShop",
+  "nearby"
+]

Changedget_public_inventory_item2 fields changed

addedOutput schema / properties

Added value: +{
+  "item": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "ok": {
+    "type": "boolean"
+  }
+}

addedOutput schema / required
```
Added value: +[
+  "ok",
+  "item"
+]
```

Changedget_public_store_inventory2 fields changed

addedOutput schema / properties

Added value: +{
+  "items": {
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "ok": {
+    "type": "boolean"
+  },
+  "returnedItems": {
+    "minimum": 0,
+    "type": "integer"
+  },
+  "store": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "totalItems": {
+    "minimum": 0,
+    "type": "integer"
+  }
+}

addedOutput schema / required

Added value: +[
+  "ok",
+  "store",
+  "items"
+]

Changedrequest_shopper_consent4 fields changed

removedInput schema / properties / agentId

Removed value: -{
-  "type": "string"
-}

changedOutput schema / additionalProperties
```
Previous value: -trueNew value: +false
```

addedOutput schema / properties

Added value: +{
+  "action": {
+    "type": "string"
+  },
+  "consentUrl": {
+    "pattern": "^https?://",
+    "type": "string"
+  },
+  "expiresAt": {
+    "type": "string"
+  },
+  "guardrails": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "ok": {
+    "const": true
+  },
+  "shopperInstruction": {
+    "type": "string"
+  },
+  "status": {
+    "type": "string"
+  },
+  "store": {
+    "additionalProperties": false,
+    "properties": {
+      "name": {
+        "type": "string"
+      },
+      "slug": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "slug",
+      "name"
+    ],
+    "type": "object"
+  }
+}

addedOutput schema / required

Added value: +[
+  "ok",
+  "status",
+  "action",
+  "store",
+  "expiresAt",
+  "consentUrl",
+  "shopperInstruction",
+  "guardrails"
+]

Changedsearch_local_inventory5 fields changed

removedInput schema / properties / metro

Removed value: -{
-  "description": "Optional caller-supplied metro slug, such as minneapolis-st-paul. SAGE does not infer precise shopper location.",
-  "type": "string"
-}

changedInput schema / properties / query / description

Previous value: -"Product or need to search for, such as 'pinot noir', 'Catan', or 'denim jacket'."New value: +"General-audience physical product or need to search for, such as 'Catan', 'denim jacket', or 'out-of-print field guide'."

changedInput schema / properties / vertical / description

Previous value: -"Optional vertical filter such as thrift, books, records, comics, craft, grocery, cannabis, coffee, or liquor."New value: +"Optional general-audience vertical filter such as thrift, books, records, comics, craft, grocery, or coffee."

addedOutput schema / properties

Added value: +{
+  "items": {
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "locationIntent": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "networkItems": {
+    "maxItems": 0,
+    "type": "array"
+  },
+  "ok": {
+    "type": "boolean"
+  },
+  "query": {
+    "type": "string"
+  },
+  "recovery": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "resultCount": {
+    "minimum": 0,
+    "type": "integer"
+  }
+}

addedOutput schema / required

Added value: +[
+  "ok",
+  "query",
+  "items",
+  "networkItems",
+  "resultCount",
+  "recovery"
+]

7 tool updatesJul 18, 2026
- First observedfetch
- First observedfind_inventory_alternatives
- First observedget_public_inventory_item
- First observedget_public_store_inventory
- First observedrequest_shopper_consent
- First observedsearch
- First observedsearch_local_inventory

Related MCP Connectors

Heartly Deals — Live Flash Sales (Shopify & WooCommerce)A
io.heartly
Live flash-sale inventory from verified Shopify and WooCommerce merchants worldwide.
E-commerce & Retail Marketing
32
UNITEMFG U.S. Manufacturer Directory
com.unitemfg
Search verified U.S. manufacturers with provenance, freshness, and live directory statistics.
Search Open Data Research & Data
1
AgentsPrice A
com.agentsprice
Verified best price across crypto, retail, tools & Rx generics — real sellers, never fabricated.
E-commerce & Retail Search
2
iwant.fyi - shop, price-check and keep looking A
fyi.iwant
No key needed. Search real products and live dealer inventory, price-check, keep standing wants.
E-commerce & Retail Search
132

Related MCP Servers

droplinked MCP Extensionofficial
E-commerce & Retail Blockchain
droplinked
A
license
A
quality
B
maintenance
Enables read-only discovery and verification of products across droplinked's KYB-attested merchant network via tools for inventory, merchant, and brand attestation lookups.
Updated 2 months ago (2026-08-03 22:53 UTC)
7
MIT
daxoom
Search E-commerce & Retail Location Services
CITROOT
F
license
Not graded
quality
F
maintenance
The owner-verified local business data + service & menu-price layer for AI agents. Owner-authored business profiles where every response carries provenance — verification level, completeness score, freshness timestamps, and upstream sources. * Search & profiles — find businesses by name, category, city, or geo-radius; full profiles with contacts, hours, media, ratings. * Price layer
Updated 3 months ago (2026-06-19 16:27 UTC)
-
Reverb
E-commerce & Retail Search
pipeworx-io
A
license
Not graded
quality
C
maintenance
Enables AI agents to search live musical-instrument marketplace listings — guitars, amps, pedals, synths, drums and pro audio — filtering by make, model, category, condition, price band, year and region, and to pull full listing detail, seller profiles and the category tree. It returns current asking prices only, with no realized sold-transaction data.
Updated 3 days ago (2026-09-25 02:08 UTC)
9 npm
MIT
Agentic Product Protocol MCP
E-commerce & Retail Search
AiAgentKarl
A
license
A
quality
D
maintenance
Klarna-style product discovery for AI shopping agents. Makes product catalogs machine-readable so AI agents can search, compare, and purchase products programmatically.
Updated 6 months ago (2026-03-20 11:47 UTC)
6
MIT