# SupplyGraph.AI (remote · mcp.supplygraph.ai)

Official MCP: continuous supply-chain risk monitoring and early warning, not a one-off report.

- Trust score: 75/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-26

## Components

- remote · `mcp.supplygraph.ai`: 75/100 (this document), [markdown](https://verifymcp.io/servers/supplygraphai-supplygraph/mcp.md), [page](https://verifymcp.io/servers/supplygraphai-supplygraph/mcp)

## Channel facts

- Endpoint: `https://mcp.supplygraph.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-26.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1970 tokens (~218/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the SupplyGraph.AI MCP server?

SupplyGraph.AI is a hosted endpoint at https://mcp.supplygraph.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http supplygraphai-supplygraph 'https://mcp.supplygraph.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "supplygraphai-supplygraph": {
      "url": "https://mcp.supplygraph.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "supplygraphai-supplygraph": {
      "type": "http",
      "url": "https://mcp.supplygraph.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.supplygraphai-supplygraph]
url = "https://mcp.supplygraph.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "supplygraphai-supplygraph": {
      "type": "remote",
      "url": "https://mcp.supplygraph.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add supplygraphai-supplygraph --url 'https://mcp.supplygraph.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  supplygraphai-supplygraph:
    url: "https://mcp.supplygraph.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "supplygraphai-supplygraph": {
      "Transport": "http",
      "Url": "https://mcp.supplygraph.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add supplygraphai-supplygraph -t streamable-http -u 'https://mcp.supplygraph.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "supplygraphai-supplygraph": {
      "type": "http",
      "url": "https://mcp.supplygraph.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-25 (score 75, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-18 (score 75, +1)

- [security] Stability: 0.97 → pass

### 2026-09-16 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 69, +46)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.57

## MCP tools (9)

### `due_diligence_report` (~863 tokens)

Supplier Due Diligence Report Agent

Generates comprehensive supplier due diligence reports using global enterprise data, benchmarking ownership, legal, and financial risk for compliance and procurement decisions.

Pricing: {"unit": "credits", "options": [{"chapter_name": "Company Registration Information", "per_run": 1518}, {"chapter_name": "Branch Offices", "per_run": 1650}, {"chapter_name": "Corporate Brand Initiatives", "per_run": 2079}, {"chapter_name": "Administrative Sanctions", "per_run": 1485}, {"chapter_name": "Software Copyright Details", "per_run": 1551}, {"chapter_name": "Outbound Investments", "per_run": 1650}, {"chapter_name": "Financing Activities", "per_run": 1452}, {"chapter_name": "Competitor Analysis", "per_run": 1485}, {"chapter_name": "Subsidiary Companies", "per_run": 1848}, {"chapter_name": "Trademark Portfolio", "per_run": 4059}, {"chapter_name": "Patent Holdings", "per_run": 12045}, {"chapter_name": "Website Registrations", "per_run": 1419}, {"chapter_name": "Court Judgments", "per_run": 1584}, {"chapter_name": "Shareholder Structure", "per_run": 1386}, {"chapter_name": "Senior Management Team", "per_run": 1452}, {"chapter_name": "Administrative Permits", "per_run": 1749}, {"chapter_name": "Court Hearing Notices", "per_run": 3696}, {"chapter_name": "Court Notices", "per_run": 3597}, {"chapter_name": "Equity Pledges", "per_run": 1419}, {"chapter_name": "Mobile Applications", "per_run": 1386}, {"chapter_name": "Copyrighted Works", "per_run": 1749}, {"chapter_name": "Equity Freezes", "per_run": 1419}, {"chapter_name": "Chattel Mortgages", "per_run": 1419}, {"chapter_name": "WeChat Official Accounts", "per_run": 1386}, {"chapter_name": "Tendering and Bidding Activities", "per_run": 2145}, {"chapter_name": "Qualification Certificates", "per_run": 2310}, {"chapter_name": "Engineering Irregularities", "per_run": 1419}, {"chapter_name": "Major Regulatory Violations", "per_run": 1452}, {"chapter_name": "Compensation and Benefits", "per_run": 1386}, {"chapter_name": "Enforcement Target…

Input parameters:

- `chapter_name` (string): Report chapter to generate. Omit or use ALL for the full due diligence report.
- `pid` (string, required): Internal company ID for the target enterprise, obtained from the search_company_candidates MCP tool (e.g. a77828f060c866441f2403384b271e63 for Tesla, Inc.).

### `tariff_calc` (~110 tokens)

U.S. Tariff Calculation Agent

Calculates U.S. customs duties by combining HTS base rates with applicable Chapter 99 measures, providing transparent, rule-based tariff outcomes.

Pricing: {"unit": "credits", "per_run": 10}

Input parameters:

- `country_or_region` (string, required): Country or region of origin for the imported product, e.g. China, Mexico, European Union.
- `product_description` (string, required): Description of the product to import into the United States, e.g. HS code, product name, material, or specifications.

### `corporate_exception_report` (~297 tokens)

Corporate Exception Report

Enterprise Change Report

Pricing: {"unit": "credits", "options": [{"chapter_name": "License", "per_run": 1518}, {"chapter_name": "GovRel", "per_run": 1419}, {"chapter_name": "R&D", "per_run": 1749}, {"chapter_name": "Reputation", "per_run": 8481}, {"chapter_name": "Ops", "per_run": 1749}, {"chapter_name": "GeneralRisks", "per_run": 1617}, {"chapter_name": "Profile", "per_run": 1749}, {"chapter_name": "Cost", "per_run": 1386}, {"chapter_name": "Compliance", "per_run": 1419}, {"chapter_name": "Competition", "per_run": 1452}, {"chapter_name": "Brand", "per_run": 3168}, {"chapter_name": "HR", "per_run": 1419}, {"chapter_name": "ALL", "per_run": 26400}]}

Input parameters:

- `chapter_name` (string): Exception domain chapter to generate. Omit or use ALL for the full corporate exception report.
- `pid` (string, required): Internal company ID for the target enterprise, obtained from the search_company_candidates MCP tool (e.g. a77828f060c866441f2403384b271e63 for Tesla, Inc.).

### `search_company_candidates` (~108 tokens)

Search Company Candidates

Search company candidates by company name, optionally filtered by country or region, and return possible matching records with mapped company IDs for caller-side selection.

Pricing: {"unit": "credits", "billing_model": "per_run", "per_run": 1}

Input parameters:

- `text` (string, required): Company name with optional country or region. The input should contain a company name, and may optionally include its country or region (e.g. 'Tesla United States', 'Samsung South Korea', 'Huawei Chi…

### `sg_chokepoint` (~131 tokens)

Geographic Concentration Analysis Agent

Analyzes multi-tier supply chains to detect single-country concentration and quantify geographic dependency across regions.

Pricing: {"unit": "credits", "per_run": 264590}

Input parameters:

- `pid` (string, required): Internal company ID for the target enterprise, obtained from the search_company_candidates MCP tool (e.g. a77828f060c866441f2403384b271e63 for Tesla, Inc.).
- `region_name` (string, required): Standardized country or region name for geographic concentration analysis, obtained from the search_region_candidates MCP tool (e.g. China, United States, Hong Kong).

### `sg_visualization` (~88 tokens)

Enterprise Supply Graph Visualization Agent

Generates global multi-tier supply-chain graphs providing full visibility into enterprise and product dependencies.

Pricing: {"unit": "credits", "per_run": 264590}

Input parameters:

- `pid` (string, required): Internal company ID for the target enterprise, obtained from the search_company_candidates MCP tool (e.g. a77828f060c866441f2403384b271e63 for Tesla, Inc.).

### `tariff_classification` (~69 tokens)

Customs Classification Agent

Classifies products into correct HTS codes from text or documents, automating tariff lookup and ensuring customs compliance in real time.

Pricing: {"unit": "credits", "per_run": 2}

Input parameters:

- `product_description` (string, required): Description of the product used to identify HS/HTS codes.

### `search_region_candidates` (~131 tokens)

Search Region Candidates

Resolves natural-language country or region names (including aliases and abbreviations) against SupplyGraph’s internal geography registry and returns a list of standardized region names for downstream agent and MCP tool consumption.

Pricing: {"unit": "credits", "billing_model": "per_run", "per_run": 1}

Input parameters:

- `text` (string, required): Country or region name in natural language, including aliases and abbreviations (e.g. 'China', 'USA', 'South Korea', 'Hong Kong', '中国', '美国'). The tool searches the internal geography registry and re…

### `supply_chain_risk_prediction` (~81 tokens)

Supply Chain Risk Prediction Agent

Continuously monitors global supply chain risk events and evaluates whether, how, and to what extent those events may affect a target company.

Pricing: {"unit": "credits", "per_run": 264590}

Input parameters:

- `event_info` (object, required): Evaluates how a supply chain risk event may affect a target company through multi-tier supply chain propagation analysis.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/supplygraphai-supplygraph/mcp#diagnostics

## Score history

- 2026-09-26: 75
- 2026-09-25: 75
- 2026-09-24: 75
- 2026-09-23: 75
- 2026-09-22: 75
- 2026-09-21: 75
- 2026-09-20: 75
- 2026-09-19: 75
- 2026-09-18: 75
- 2026-09-17: 74
- 2026-09-16: 74
- 2026-09-15: 73
- 2026-09-14: 73
- 2026-09-13: 72
- 2026-09-12: 72
- 2026-09-11: 71
- 2026-09-10: 71
- 2026-09-09: 70
- 2026-09-08: 70
- 2026-09-07: 69
- 2026-09-06: 69
- 2026-09-05: 69
- 2026-09-04: 23
- 2026-09-03: 68
- 2026-09-02: 67
- 2026-09-01: 67
- 2026-08-31: 66
- 2026-08-30: 66
- 2026-08-29: 65
- 2026-08-28: 65

## Common questions

### What is the SupplyGraph.AI MCP server?

SupplyGraph.AI is an MCP server listed in the public MCP registry as io.github.SupplyGraphAI/supplygraph. Official MCP: continuous supply-chain risk monitoring and early warning, not a one-off report. This page covers its hosted endpoint (https://mcp.supplygraph.ai/mcp).

### Is the SupplyGraph.AI MCP server safe to use?

SupplyGraph.AI scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the SupplyGraph.AI MCP server expose?

SupplyGraph.AI exposes 9 tools: due_diligence_report, tariff_calc, corporate_exception_report, search_company_candidates, sg_chokepoint, and 4 more. Their descriptions and schemas cost roughly 1,878 tokens of context every time the server is loaded.

### Does the SupplyGraph.AI MCP server require authentication?

No. We connected to SupplyGraph.AI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the SupplyGraph.AI MCP server still maintained?

SupplyGraph.AI is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.supplygraph.ai/mcp
- Website: https://supplygraph.ai/resources/mcp
- Changelog RSS feed: https://verifymcp.io/servers/supplygraphai-supplygraph/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/supplygraphai-supplygraph/mcp.json
- HTML version of this page: https://verifymcp.io/servers/supplygraphai-supplygraph/mcp