Databases

partsgraph.ai

Provides a searchable parts catalogue with provenance, reference builds, and compatibility checking for engineering projects.

1 endpoint11 known toolsFirst detected August 20, 2026Last detected September 4, 2026

ENDPOINT 1

https://partsgraph.ai/api/mcp

No auth detected

MCP server metadata

Name: partsgraph-catalog
Version: 1.4.0

Capabilities

tools.listChangedresources.listChangedprompts.listChangedcompletions

Server instructions

The Partsgraph demo catalogue: 35 provenance-backed part records and three reference builds. Search parts, read full records with datasheet provenance, check compatibility, and compose validated BOMs. Prices are indicative and dated; availability is never claimed. Filling project_context ranks results for your build. Tool calls are logged anonymously (salted-hash network address, no identity) to power the public demo dashboard.

Known tools 11

search_parts

Full-text search over the demo catalogue's provenance-backed part records.

Inferred read-only

get_part

The complete canonical record for one part: every attribute with its provenance (source, page, verbatim quote, file hash), vendors with dated indicative prices, and datasheet links.

Inferred read-only

list_categories

Every category in the catalogue with its part count.

Inferred read-only

list_builds

The catalogue's reference builds (robot, weather station, plant waterer) with their roles and candidate parts — the starting point for build_bom.

Inferred read-only

check_compatibility

Evaluates a part set against the build's engineering constraints — supply windows, stall vs peak current, shaft/wheel fit, interfaces, solar chain — with a reasoned verdict per check.

Inferred read-only

compare_parts

Aligned attribute-by-attribute comparison of two catalogue parts.

Inferred read-only

get_provenance

The receipt behind a stated value: the verbatim source quote, the page, the extraction method, and the sha-256 of the exact file it was read from — plus a ready-made citation line.

Inferred read-only

build_bom

Composes a complete BOM for a reference build — quantities, dated indicative prices, per-line rationale, a compatibility verdict for the chosen set, and a CSV export.

Inferred read-only

search

Search the Partsgraph demo catalogue.

Inferred read-only

fetch

Fetch the full provenance-backed record for a search result id as a citable document.

Inferred read-only

view_bom

Composes the BOM for a reference build and renders it as an interactive view in clients that support MCP Apps.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.partsgraph-catalog]
url = "https://partsgraph.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "partsgraph-catalog": {
      "type": "http",
      "url": "https://partsgraph.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: partsgraph-catalog
Remote MCP URL: https://partsgraph.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "partsgraph-catalog": {
      "url": "https://partsgraph.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "partsgraph-catalog": {
      "type": "http",
      "url": "https://partsgraph.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "partsgraph-catalog",
  "transport": "streamable-http",
  "url": "https://partsgraph.ai/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for partsgraph.ai was fetched 2026-08-24T02:35:09.723Z.

Trust status Neutral

partsgraph.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.