Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

SupplyGraph.AI

REMOTE · MCP.SUPPLYGRAPH.AI · SCANNED SEP 26

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

0 this week 75 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability63
  • AI-judged instruction clarity (excellent).Pass
  • 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. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.

remote · mcp.supplygraph.ai

# add to Claude Code
claude mcp add --transport http supplygraphai-supplygraph 'https://mcp.supplygraph.ai/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "supplygraphai-supplygraph": {
      "url": "https://mcp.supplygraph.ai/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "supplygraphai-supplygraph": {
      "type": "http",
      "url": "https://mcp.supplygraph.ai/mcp"
    }
  }
}
# ~/.codex/config.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
    }
  }
}
# add to OpenClaw
openclaw mcp add supplygraphai-supplygraph --url 'https://mcp.supplygraph.ai/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  supplygraphai-supplygraph:
    url: "https://mcp.supplygraph.ai/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "supplygraphai-supplygraph": {
      "Transport": "http",
      "Url": "https://mcp.supplygraph.ai/mcp"
    }
  }
}
# add to Vellum
assistant mcp add supplygraphai-supplygraph -t streamable-http -u 'https://mcp.supplygraph.ai/mcp'
// mcp.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 we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 18 Sept 26 +1
    • Stability: 0.97 → pass security
  • 16 Sept 26 +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.

  • 14 Sept 26 +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.

  • 12 Sept 26 +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.

  • 10 Sept 26 +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.

  • 8 Sept 26 +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.

  • 5 Sept 26 +46
    • Injection markers: unverified → pass ▲ security
    • 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. security
    • MCP protocol: unverified → fail ▼ functional
    • Endpoint reachability: not serving MCP → reachable ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • Stability: unverified → 0.57 ▲ functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 26 Sept 2026 · Probed https://mcp.supplygraph.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=supplygraph.ai CN=YR1,O=Let's Encrypt,C=US 31 Aug 2026 29 Nov 2026 RSA 2048 SHA256-RSA 53d40d6ae2d47509e53d894f6bafa7c6606
SANs: agent.supplychaindata.ai, agent.supplygraph.ai, agentts.supplygraph.ai, ey.supplygraph.ai, fts.supplychaindata.ai, fts.supplygraph.ai, mapcollective.supplygraph.ai, mcp.supplygraph.ai, mcpts.supplygraph.ai, supplychaindata.ai, supplygraph.ai, test.supplychaindata.ai and 4 more
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.supplygraph.ai. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
supplygraph.ai. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.supplygraph.ai/mcp Verified 200
http (plaintext) http://mcp.supplygraph.ai/mcp HTTPS enforced 301 https://mcp.supplygraph.ai/mcp
MCP tools · 9 exposed · ~1,878 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
corporate_exception_report ~297

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}]}

NameTypeReqDescription
chapter_namestring–Exception domain chapter to generate. Omit or use ALL for the full corporate exception report.
pidstringyesInternal company ID for the target enterprise, obtained from the search_company_candidates MCP tool (e.g. a77828f060c866441f2403384b271e63 for Tesla, Inc.).

Structured output declared, but exposes no named fields.

No examples provided.

due_diligence_report ~863

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…

NameTypeReqDescription
chapter_namestring–Report chapter to generate. Omit or use ALL for the full due diligence report.
pidstringyesInternal company ID for the target enterprise, obtained from the search_company_candidates MCP tool (e.g. a77828f060c866441f2403384b271e63 for Tesla, Inc.).

Structured output declared, but exposes no named fields.

No examples provided.

search_company_candidates ~108

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}

NameTypeReqDescription
textstringyesCompany 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…

Structured output declared, but exposes no named fields.

No examples provided.

search_region_candidates ~131

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}

NameTypeReqDescription
textstringyesCountry 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…

Structured output declared, but exposes no named fields.

No examples provided.

sg_chokepoint ~131

Analyzes multi-tier supply chains to detect single-country concentration and quantify geographic dependency across regions. Pricing: {"unit": "credits", "per_run": 264590}

NameTypeReqDescription
pidstringyesInternal company ID for the target enterprise, obtained from the search_company_candidates MCP tool (e.g. a77828f060c866441f2403384b271e63 for Tesla, Inc.).
region_namestringyesStandardized country or region name for geographic concentration analysis, obtained from the search_region_candidates MCP tool (e.g. China, United States, Hong Kong).

Structured output declared, but exposes no named fields.

No examples provided.

sg_visualization ~88

Generates global multi-tier supply-chain graphs providing full visibility into enterprise and product dependencies. Pricing: {"unit": "credits", "per_run": 264590}

NameTypeReqDescription
pidstringyesInternal company ID for the target enterprise, obtained from the search_company_candidates MCP tool (e.g. a77828f060c866441f2403384b271e63 for Tesla, Inc.).

Structured output declared, but exposes no named fields.

No examples provided.

supply_chain_risk_prediction ~81

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}

NameTypeReqDescription
event_infoobjectyesEvaluates how a supply chain risk event may affect a target company through multi-tier supply chain propagation analysis.

Structured output declared, but exposes no named fields.

No examples provided.

tariff_calc ~110

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}

NameTypeReqDescription
country_or_regionstringyesCountry or region of origin for the imported product, e.g. China, Mexico, European Union.
product_descriptionstringyesDescription of the product to import into the United States, e.g. HS code, product name, material, or specifications.

Structured output declared, but exposes no named fields.

No examples provided.

tariff_classification ~69

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}

NameTypeReqDescription
product_descriptionstringyesDescription of the product used to identify HS/HTS codes.

Structured output declared, but exposes no named fields.

No examples provided.

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.