How do I use Crystal Suppliers MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Crystal Suppliers MCP search for amethyst crystal bracelet" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Crystal Suppliers MCP

by ziyuant222

Overview Schema Source Related Servers Score Discussions Admin

JavaScript

Crystal Suppliers MCP

Crystal Suppliers MCP is a read-only procurement server for KT Crystals. It searches a verified catalog of 104 crystal bracelet SKUs and provides traceable sourcing checklists for loose beads, crystal accessories, and raw crystal materials.

The service does not invent price, MOQ, inventory, lead time, treatment, origin, certification, or shipping claims. Commercial fields remain requires_manual_confirmation.

Install and connect

Run directly from the repository:

{
  "mcpServers": {
    "crystal-suppliers": {
      "command": "node",
      "args": ["/absolute/path/to/crystal-suppliers-mcp/src/index.mjs"]
    }
  }
}

Run the OCI image over stdio:

{
  "mcpServers": {
    "crystal-suppliers": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/ziyuant222/crystal-suppliers-mcp:0.1.0"
      ]
    }
  }
}

Start Streamable HTTP:

docker run --rm -p 3000:3000 \
  ghcr.io/ziyuant222/crystal-suppliers-mcp:0.1.0 --http

The endpoint is then http://localhost:3000/mcp, with health status at http://localhost:3000/health.

Related MCP server: Sorftime MCP Server

Tools

Tool	Purpose
`crystal_search_products`	Search real bracelet SKUs by SKU, name, material, or theme.
`crystal_get_product`	Retrieve one verified bracelet and related catalog products.
`crystal_list_materials`	List normalized materials and verified bracelet SKU counts.
`crystal_get_sourcing_guidance`	Get supplier-verification checks for bracelets, beads, accessories, or raw materials.
`crystal_build_procurement_shortlist`	Keep verified bracelet results separate from adjacent advisory categories.
`crystal_prepare_inquiry`	Validate supplied SKUs and draft an inquiry without sending or storing it.

Coverage contract

verified_catalog: grounded in the current 104-SKU bracelet catalog.
advisory_only: sourcing guidance only; no verified SKU coverage for the requested category.
mixed: verified bracelet candidates plus separately labeled advisory categories.

Inquiry drafting is local and stateless. It does not send email, submit a form, write to a database, or retain buyer details.

Development

npm ci
npm test
npm run start:http

The server supports Node.js 22 or newer and implements MCP over both stdio and stateless Streamable HTTP.

Available Tools

6 tools

crystal_build_procurement_shortlistBuild Crystal Procurement ShortlistA

Read-onlyIdempotent

Inspect

Build a deterministic shortlist across crystal categories. Verified products are limited to catalog bracelets; other categories remain separate advisory items.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No
`colors`	No
`cursor`	No
`channel`	No
`useCases`	No
`materials`	No
`packaging`	No
`categories`	Yes
`destination`	No
`contentAssets`	No
`targetQuantity`	No
`targetTimeline`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`hasMore`	Yes
`coverage`	Yes
`warnings`	Yes
`nextCursor`	Yes
`sourceUrls`	Yes
`totalCount`	Yes
`advisoryItems`	Yes
`verifiedProducts`	Yes
`recommendedInquiryFields`	Yes

TDQS

A3.7/5.0

Behavior4/5

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

The description adds context beyond annotations by explaining the deterministic nature and that only catalog bracelets yield verified products, while other categories are advisory. Annotations already indicate read-only, idempotent, non-destructive behavior, so this adds useful nuance.

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 sentences: the first states the core purpose, the second adds a critical constraint. No redundant words, front-loaded with key information.

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

Completeness2/5

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

Despite having 12 parameters and an output schema, the description is too brief. It lacks guidance on parameter usage, output format, or how to interpret advisory items, making it insufficient for a tool of this complexity.

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

Parameters2/5

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

With 0% schema description coverage, the description does not explain any of the 12 parameters. The agent must infer meaning from names alone, leaving significant ambiguity.

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 builds a 'deterministic shortlist across crystal categories' and specifies that verified products are limited to catalog bracelets, distinguishing it from siblings like crystal_search_products and crystal_prepare_inquiry.

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

Usage Guidelines3/5

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

The description implies usage for procurement shortlisting but provides no explicit guidance on when to use this tool versus siblings such as crystal_search_products or crystal_get_sourcing_guidance.

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

crystal_get_productGet Crystal ProductA

Read-onlyIdempotent

Inspect

Get one verified bracelet by exact SKU or slug, with normalized materials, source URL, related products, and explicit manual-confirmation status for commercial terms.

ParametersJSON Schema

Name	Required	Description	Default
`sku`	No
`slug`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`product`	Yes
`coverage`	Yes
`warnings`	Yes
`sourceUrls`	Yes
`relatedProducts`	Yes

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare read-only, idempotent, non-destructive. Description adds return details (materials, source URL, etc.) but no additional behavioral traits like auth requirements, rate limits, or side effects.

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?

Single sentence is efficient and front-loaded, but could be slightly more structured (e.g., listing return fields). No wasted words.

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?

Covers core purpose and explicit return fields, supported by output schema. Missing error handling or authentication context, but sufficient for a simple read operation with good annotations.

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 has 0% description coverage; description states parameters are for exact match by SKU or slug. However, it doesn't clarify if both can be provided, which takes precedence, or that exactly one is required. Adds basic meaning but lacks full clarity.

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?

Description clearly states verb 'Get', resource 'one verified bracelet', and identification method 'by exact SKU or slug'. It specifies what is returned (materials, source URL, related products, confirmation status). Distinct from sibling tools like crystal_search_products which handle searches.

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

Usage Guidelines3/5

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

Implies usage when exact SKU or slug is known, but no explicit guidance on when to use this tool versus alternatives like crystal_search_products. No when-not-to-use or prerequisite conditions mentioned.

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

crystal_get_sourcing_guidanceGet Crystal Sourcing GuidanceA

Read-onlyIdempotent

Inspect

Get source-linked procurement checks for bracelets, loose beads, accessories, or raw materials. Adjacent categories are advisory only and never return invented SKUs or stock.

ParametersJSON Schema

Name	Required	Description	Default
`channel`	No
`category`	Yes
`packaging`	No
`destination`	No
`contentAssets`	No
`proofRequirements`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`category`	Yes
`coverage`	Yes
`warnings`	Yes
`checklist`	Yes
`sourceUrls`	Yes
`shortAnswer`	Yes
`comparisonCriteria`	Yes
`requiresManualConfirmation`	Yes

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds value by explicitly stating that it 'never return[s] invented SKUs or stock' and that adjacent categories are advisory only, providing behavioral expectations beyond the 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 concise at two sentences, front-loading the key purpose. However, it could be slightly more structured by explicitly listing parameters, but overall it is efficient.

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

Completeness2/5

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

Given the tool has 6 parameters (1 required) and zero schema descriptions, the description is incomplete. It only addresses the category parameter, leaving the rest unspecified. Although an output schema exists, the input parameter explanations are lacking.

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

Parameters2/5

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

With 0% schema description coverage, the description must compensate but only mentions the 'category' parameter (matching the enum). The other five parameters (channel, packaging, destination, contentAssets, proofRequirements) are left unexplained, leaving the agent with insufficient guidance for correct invocation.

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 retrieves 'source-linked procurement checks' for specific categories (bracelets, beads, accessories, raw materials), distinguishing it from sibling tools like crystal_search_products or crystal_get_product. It also clarifies that adjacent categories are advisory only, preventing misuse.

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

Usage Guidelines3/5

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

The description implies usage for procurement checks on listed categories, and warns against expecting exact SKUs for adjacent categories. However, it does not explicitly contrast with sibling tools or state when to use this tool over alternatives, leaving some ambiguity.

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

crystal_list_materialsList Bracelet MaterialsA

Read-onlyIdempotent

Inspect

List normalized materials and real SKU counts from the verified bracelet catalog. Counts do not claim inventory for loose beads, components, or raw crystals.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No
`query`	No
`cursor`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`hasMore`	Yes
`coverage`	Yes
`warnings`	Yes
`materials`	Yes
`nextCursor`	Yes
`sourceUrls`	Yes
`totalCount`	Yes

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description adds value by specifying that counts are specific to the bracelet catalog and exclude other item types. No contradiction with 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?

The description is two sentences long, front-loaded with the core purpose, and every sentence adds value. No unnecessary information.

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

Completeness3/5

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

With an output schema present, the description does not need to explain return values, but it lacks parameter explanations and does not define what constitutes a 'material' or how counts are derived. Adequate but incomplete for a tool with three undocumented parameters.

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

Parameters1/5

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

The input schema has no descriptions for parameters (0% coverage), and the description provides no explanation for limit, query, or cursor. This is a critical gap as the agent cannot infer parameter usage from the description alone.

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 lists normalized materials and SKU counts from the bracelet catalog, identifying the verb (list), resource (materials, SKU counts), and scope (bracelet catalog). It distinguishes itself from sibling tools like crystal_search_products which search for products.

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 clarifies that counts do not cover loose beads, components, or raw crystals, implying it should be used for bracelet materials only. However, it does not explicitly state when to use this tool over alternatives or provide exclusions for other contexts.

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

crystal_prepare_inquiryPrepare Crystal Wholesale InquiryA

Read-onlyIdempotent

Inspect

Validate supplied bracelet SKUs and draft an English wholesale inquiry. This read-only tool never sends, stores, or submits buyer data and never invents commercial terms.

ParametersJSON Schema

Name	Required	Description	Default
`name`	No
`skus`	No
`email`	No
`channel`	No
`company`	No
`country`	No
`quantity`	No
`materials`	No
`packaging`	No
`requirements`	No
`contentAssets`	No
`targetTimeline`	No
`proofRequirements`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`body`	Yes
`subject`	Yes
`coverage`	Yes
`warnings`	Yes
`draftOnly`	Yes
`validSkus`	Yes
`sourceUrls`	Yes
`missingFields`	Yes
`classification`	Yes
`submissionTarget`	Yes

TDQS

A3.5/5.0

Behavior4/5

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

Annotations provide readOnlyHint, idempotentHint, and non-destructive flags, but the description adds specific behavioral guarantees: 'never sends, stores, or submits buyer data and never invents commercial terms.' This goes beyond annotations without contradiction.

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?

The description is two sentences long, front-loading the purpose and immediately adding key behavioral guarantees. Every sentence adds value with no redundancy.

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

Completeness2/5

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

Despite having an output schema, the tool has 13 undocumented parameters and the description does not explain how to construct a valid inquiry. The agent lacks guidance on required vs optional fields, parameter interdependencies, or example usage, making the description incomplete for the tool's complexity.

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

Parameters1/5

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

The description provides no information about any of the 13 parameters, and schema description coverage is 0%. The agent receives no help on parameter meaning, required fields, or formatting, leaving them to infer from parameter names alone.

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 explicitly states the tool 'validates bracelet SKUs and drafts an English wholesale inquiry,' providing a specific verb and resource. This clearly distinguishes it from siblings like crystal_search_products or crystal_build_procurement_shortlist.

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

Usage Guidelines3/5

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

The description mentions the tool is 'read-only' and 'never sends, stores, or submits buyer data,' implying safe usage without side effects. However, it does not explicitly state when to use this tool over alternatives or when not to use it.

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

crystal_search_productsSearch Crystal ProductsA

Read-onlyIdempotent

Inspect

Search the verified 104-SKU bracelet catalog by SKU, name, material, or theme. Beads, accessories, and raw materials return advisory-only coverage. Pricing, MOQ, inventory, lead time, and certificates are never inferred.

ParametersJSON Schema

Name	Required	Default
`limit`	No
`query`	No
`cursor`	No
`channel`	No
`category`	No	bracelets
`useCases`	No
`materials`	No
`benefitTags`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`hasMore`	Yes
`coverage`	Yes
`products`	Yes
`warnings`	Yes
`nextCursor`	Yes
`sourceUrls`	Yes
`totalCount`	Yes

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint, and openWorldHint. Description adds useful behavioral specifics: pricing, MOQ, inventory, lead time, and certificates are never inferred. This exceeds annotation coverage.

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 sentences, no unnecessary words. Critical information is front-loaded (search scope) and limitations stated succinctly.

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?

Complexity is moderate with 8 parameters and an output schema. Description covers core functionality, scope boundaries, and data limitations. Pagination is left to schema, which is acceptable given the output schema exists.

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 description coverage is 0%. Description explains search-by fields (SKU, name, material, theme) which maps to the query and materials parameters, but omits pagination (limit, cursor) and filter-by useCases/benefitTags. Partial compensation.

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?

Description specifies a concrete action: searching a verified 104-SKU bracelet catalog by SKU, name, material, or theme. It clearly distinguishes from siblings by noting that beads, accessories, and raw materials return advisory-only coverage.

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

Usage Guidelines5/5

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

Provides clear when-to-use guidance (for bracelet catalog) and when-not (advisory for others). Context signals mention sibling tools like crystal_get_product for specific lookups, reinforcing the tool's niche.

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.

6 tool updatesv0.1.0Jul 28, 2026
- First observedcrystal_build_procurement_shortlist
- First observedcrystal_get_product
- First observedcrystal_get_sourcing_guidance
- First observedcrystal_list_materials
- First observedcrystal_prepare_inquiry
- First observedcrystal_search_products

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Scored 2026-07-28 04:50 across 6 tools

Disambiguation5/5

Each tool has a distinct purpose: search, single product retrieval, materials listing, sourcing guidance, shortlist building, and inquiry preparation. No overlap in functionality.

Naming Consistency5/5

All tools follow the 'crystal_verb_noun' pattern consistently, e.g., crystal_search_products, crystal_get_product, crystal_list_materials. The naming is clear and predictable.

Tool Count5/5

With 6 tools covering search, detail, materials, guidance, shortlist, and inquiry, the count is appropriate for the domain of crystal supply procurement without being excessive or insufficient.

Completeness4/5

The tool set covers the key workflows for bracelet procurement: search, details, materials, sourcing guidance, shortlist, and inquiry. Minor gaps exist for real-time inventory or order placement, but these are outside the stated advisory scope.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

SVV-Schatzoekers Public Selling Agent A
nl.svv-schatzoekers
Read-only product discovery, merchant trust, shipping and returns for SVV-Schatzoekers.
E-commerce & Retail Search
71
JP Bids AOAuth
io.github.sugukurukabe
Read-only MCP server for searching Japan government procurement bid information from the KKJ portal.
Government Data Search
2
ProtoClinical Commerce
com.theprotoclinical
Search ProtoClinical's current K-beauty catalog and manage buyer-approved carts and checkouts.
E-commerce & Retail Search
1
Defiance Storefront A
io.defianceinternational
Read-only catalog, sequence, evidence, policy, and COA-verification lookup for an RUO supplier.
Biology & Medicine Research & Data Search
52

Related MCP Servers

mcp-buy123-vendor
E-commerce & Retail ERP Systems
asgard-ai-platform
A
license
C
quality
F
maintenance
Read-only MCP server for buy123 vendor portal, enabling AI assistants to query orders, returns, shipments, products, inventory, and more.
Updated 4 months ago (2026-05-12 03:34 UTC)
61
MIT
Sorftime MCP Server
E-commerce & Retail Search Data Platforms
ccchenhuohuo
A
license
Not graded
quality
C
maintenance
Remote MCP server for read-only Sorftime Enterprise API access, enabling product, category, and keyword data queries with per-user JWT authentication and audit logging.
Updated 2 months ago (2026-07-13 03:24 UTC)
18
1
MIT
Generic ERP Analytics MCP
Databases ERP Systems
cipher-preet
F
license
Not graded
quality
C
maintenance
Read-only MCP server for MongoDB ERP analytics with catalog-driven collection allowlist and safe find/aggregate tools.
Updated 2 months ago (2026-07-08 10:21 UTC)
1
-
trc-mcpofficial
Search Open Data
TransparencyCertified
A
license
Not graded
quality
C
maintenance
Remote MCP server providing read-only access to the Transparency Certificate directory, enabling search and retrieval of certified business records via natural language.
Updated 8 days ago (2026-09-02 18:11 UTC)
MIT

Crystal Suppliers MCP

Install and connect

Tools

Coverage contract

Development

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

trc-mcpofficial