MCP servers › ai.rinda.tradegraph › tradegraph
MCP server · registry snapshot 2026-11-01 · last tested 2026-11-01
ai.rinda.tradegraph/tradegraph
by tradegraph.rinda.ai · domain (the registry's namespace rule)repository owner on GitHub: FINGU-GRINDA (organization)Source ↗Website ↗
An export sales team for consumer brands, inside your AI: markets, buyers, emails and pricing. — the publisher's description
Summary
ai.rinda.tradegraph/tradegraph is a remote MCP server listed in the official MCP registry at version 1.7.0, under the namespace of the domain tradegraph.rinda.ai. Its linked repository is github.com/FINGU-GRINDA/tradegraph; GitHub reports its owner as FINGU-GRINDA, an organization. On 2026-11-01 ProtocolProbe connected to it in read-only mode and read its inventory: 16 tools, 1 resource and 11 prompts.
Record checks
4 of 5 record checks met · 4 do not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not met: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 0 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Operate this server? Correct a fact · README badge · Run the checks yourself
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Repository
- public
- Tools
- 16
- Last tested
- 2026-11-01
Tool list size
16,449 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (16 tools). Counted with Anthropic's token counter on 2026-11-01, from the tool list we read on 2026-11-01. Median across 25,738 counted servers: 2,858 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-01 (tradegraph.rinda.ai), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.7.0).
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-01
- Mode
- read-only (no tool calls)
- Latest version
- 1.7.0, published 2026-11-01 (registry, as of the 2026-11-01 snapshot)
- First listed version
- 2026-10-29 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 2 versions listed, 2026-10-29 to 2026-11-01; 2 in the 90 days before the 2026-11-01 snapshot.(versions still listed in the registry only)
Most recent 2 versions
1.7.0· 2026-11-011.5.0· 2026-10-29
- Registry data
- snapshot 2026-11-01
- Package and repository
- checked 2026-11-01
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry; repository link does not open; repository archived; no push in over 365 days. Does not apply: listed version cannot be installed or is withdrawn. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
Version 1.5.0 (published 2026-10-29) → 1.7.0 (published 2026-11-01), between the registry lists of 2026-10-31 and 2026-11-01.
The publisher published no GitHub release note for version 1.7.0: the repository has no release tagged for it.
Source: the official MCP Registry list on 2026-10-31 and on 2026-11-01; release notes from the GitHub Releases API, checked 2026-11-01.
What it is
What does this server offer?
Observed inventoryNone of its 16 tools are described as changing anything. For 16 the reading was uncertain, so no mark is shown.
- gtm_plan
“START HERE.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
10 inputs, 1 required
countrystring“Target country as ISO 3166-1 alpha-2 (e.g.”descriptionstring“Optional: the product as the user describes it, any language (e.g.”detailstring“Optional: brief (about half the size, for chat clients with a result size limit) or full (default, every draft).”excludestring“Optional: markets already tried, comma-separated ISO codes or names (e.g.”itemstringrequired“Product as an HS4 code (e.g.”originstring“Optional: where the product is made, ISO alpha-2 (default KR, or the signed-in company's origin).”productstring“Optional: the product's own name in English for the first-email draft (e.g.”product_localstring“Optional, Japan: the product's name in Japanese for the Japanese drafts (local_emails), e.g.”strengthsstring“Optional: what your company actually offers partners, in English and your own words, up to 240 characters (e.g.”traitsstring“Optional: product traits, comma-separated, that change the rules within one HS code: sunscreen, whitening (also arbutin, kojic acid), vitamin_a (retinol), gel_…”
- blind_spotson 1 other server
“What a Korean exporter of this product is likely to miss in a market — the unknown unknowns beyond the product category's usual compliance: rules that can stop the sale (e.g.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
countrystring“Target country as ISO 3166-1 alpha-2 (e.g.”descriptionstring“Optional: the product as the user describes it, any language (e.g.”itemstringrequired“Product as an HS4 code (e.g.”productstring“Optional: the product's own name in English (e.g.”traitsstring“Optional: product traits, comma-separated, that change the rules within one HS code: sunscreen, whitening (also arbutin, kojic acid), vitamin_a (retinol), gel_…”
- reply_pace
“Weekly pace check for one market: pass the buyers emailed so far (each buyer once, first emails only), the buyers who replied (any reply, a no counts) and, if known, the week of the 13-week schedule …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
17 inputs, 4 required
bouncedinteger“Optional: buyers whose email bounced.”buyer_typestring“Optional: the buyer type the user sent to last week (last week's find_buyers_type); after a switch to the next type the check keeps it.”changedstring“Optional: changes already made in earlier weeks, as last week's changed (comma-separated: next_type, new_subject, new_subject_2, offer, retry, retry_type).”countrystringrequired“Target country as ISO 3166-1 alpha-2 (e.g.”excludestring“Optional: markets already tried, comma-separated ISO codes or names (e.g.”itemstringrequired“Product as an HS4 code (e.g.”last_repliesinteger“Optional: last week's replies total (replies lower than last_replies is rejected).”last_sentinteger“Optional: last week's sent total, to catch this week's numbers passed instead of running totals (sent lower than last_sent is rejected).”meetingsinteger“Optional: buyers who agreed to a meeting or a call.”openedinteger“Optional: of the buyers emailed, how many opened at least one email, as the user's email tool reports it (unique opens).”ordersinteger“Optional: buyers who placed an order (trial orders count).”quotesinteger“Optional: buyers who asked for prices or a quote.”repliesintegerrequired“Buyers who replied so far (any reply, including a no).”samplesinteger“Optional: buyers who asked for samples.”sentintegerrequired“Buyers emailed so far in this market (count each buyer once; follow-ups don't add).”warminteger“Optional: of the replies, how many were interested (a question, a sample request or a meeting; not a no).”weekinteger“Optional: the week of the 13-week schedule they are in (1 = the week of the first 200 emails), to flag sends behind schedule or a decision that moves past week…”
- find_item
“Resolve a product description (any of 10 languages, e.g.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
querystringrequired“Product name, alias or HS digits.”
- market_picks
“Import markets for a product ranked by size, with 3-year growth, Korea's share and the reply rate Korean exporters of that industry actually got there (reply_scope: industry = compared with the indus…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
itemstringrequired“Product as an HS4 code (e.g.”limitinteger“Markets to return.”
- buyer_targets
“Reply rates of country × buyer type (importer, distributor, wholesaler, retailer, brand, manufacturer, clinic) from 2.2M real export emails, shrunk toward the average so small samples do not mislead,…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
buyer_typestring“Optional buyer type filter.”countrystring“Target country as ISO 3166-1 alpha-2 (e.g.”limitinteger“Rows to return.”tierstring“Which confidence tiers to return.”
- country_briefon 1 other server
“Everything TradeGraph knows about one country: reply rate and best buyer types, the product's import size/growth/Korea share and supplier mix, why other Korean exporters chose it, reply rates by indu…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
countrystringrequired“Target country as ISO 3166-1 alpha-2 (e.g.”descriptionstring“Optional: the product as the user describes it, any language (e.g.”itemstring“Product as an HS4 code (e.g.”traitsstring“Optional: product traits, comma-separated, that change the rules within one HS code: sunscreen, whitening (also arbutin, kojic acid), vitamin_a (retinol), gel_…”
- export_rank
“World exporters of a product (UN Comtrade, latest year), Korea's rank and value, and where Korea already sells it most.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
itemstringrequired“Product as an HS4 code (e.g.”
- outreach_playbook
“Measured from 2.2M real export emails: replies per 10,000 emails at each follow-up step, the recommended number of emails, how many days to wait before the next one (follow_up_after_days), when repli…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- channel_plan
“GTM engineering plan for one country: creator platforms to seed on, marketplaces to research, buyer channels, local-language and disclosure rules, product compliance pointers (with an official source…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
countrystringrequired“Target country as ISO 3166-1 alpha-2 (e.g.”descriptionstring“Optional: the product as the user describes it, any language (e.g.”itemstring“Product as an HS4 code (e.g.”motionstring“Which part of the plan to return.”traitsstring“Optional: product traits, comma-separated, that change the rules within one HS code: sunscreen, whitening (also arbutin, kojic acid), vitamin_a (retinol), gel_…”
- market_scanon 1 other server
“For products outside TradeGraph's 35 items: live UN Comtrade imports by country for any 4-digit HS code (latest complete year, 3-year growth, Korea's exports there), joined with TradeGraph reply rate…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
hsstringrequired“4-digit HS code, e.g.”limitinteger“Markets to return.”
- video_studio
“Plan AI product videos for one market and platform, Higgsfield-style: preset formats (hero orbit, texture macro, unboxing POV, 3-step routine, local lifestyle, AI presenter) with camera moves, a shot…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
8 inputs, 1 required
countrystringrequired“Target country as ISO 3166-1 alpha-2 (e.g.”has_packshotboolean“Whether a real product photo exists (default true).”itemstring“Product as an HS4 code (e.g.”platformstring“Where the video runs; auto = the market's first creator platform.”presetstring“Video format; auto = three presets that suit the product group.”productstring“The product in plain English as it looks, e.g.”tierstring“Model tier: draft (cheap 480p tests), standard (Hailuo 2.3 768P), premium (Veo 3.1 Fast 1080p).”variantsinteger“Hook variants per preset (A/B test the first 2 seconds).”
Show 4 more tools
- image_studio
“Plan the product image set for one market: the marketplace's main-image rules (Amazon, Rakuten, Tmall, Shopee, TikTok Shop…), a 7-image gallery (real main image, local lifestyle, texture, how-to, ben…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
countrystringrequired“Target country as ISO 3166-1 alpha-2 (e.g.”itemstring“Product as an HS4 code (e.g.”marketplacestring“Optional marketplace, e.g.”productstring“The product in plain English as it looks.”variantsinteger“Generated variants per frame.”
- price_ladderon 1 other server
“Turn a FOB unit price into the landed cost, importer/distributor price and shelf price (incl.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
22 inputs, 1 required
channelstring“Route to the consumer or, for goods sold to businesses, to the end user.”comparestring“Optional: other markets to price the same FOB and channel in, each with its own duty and VAT defaults (your duty_pct and vat_pct stay with this country; margin…”countrystringrequired“Target country as ISO 3166-1 alpha-2 (e.g.”dealer_margin_pctnumber“Dealer margin, % of its selling price (channel 'b2b_dealer', default 25).”descriptionstring“Optional: the product's own name or a short description (e.g.”distributor_margin_pctnumber“Distributor margin, % of its selling price (channel 'distributor').”duty_pctnumber“Import duty % of CIF for your tariff line (default 0, except the US: 12.5 — the combined duty on most Korean goods since 24 Jul 2026, KORUS included — or, when…”fob_krwnumber“FOB price per unit in Korean won (e.g.”fob_usdnumber“FOB price per unit in USD.”freight_pctnumber“Freight + insurance as % of FOB (default 8).”fulfillment_usdnumber“Fulfilment per unit in USD for marketplace sales (default 4).”import_costs_pctnumber“Broker, port, inland and labelling as % of CIF (default 4).”importer_margin_pctnumber“Importer margin, % of its selling price (channel b2b: the importer-distributor selling to the end user, default 30, 35 for medical devices; b2b_dealer: 15, or …”itemstring“Product as an HS4 code (e.g.”marketplace_fee_pctnumber“Marketplace referral fee % (default 15).”parcel_usdnumber“Channel cross_border: courier from Korea to the customer's door per unit in USD (default 5, an assumption; use your courier's quote).”retail_margin_pctnumber“Retailer margin, % of its selling price.”seller_margin_pctnumber“Your margin on marketplace sales, % of price (default 25).”target_shelf_localnumber“The same target in the market's own currency (e.g.”target_shelf_usdnumber“Shelf price you want per unit in USD (incl.”targetsstring“Optional: several shelf prices in USD to compare, comma-separated (e.g.”vat_pctnumber“Override the VAT/GST rate.”
- live_tools
“Search the treg.to catalog (3,800+ endpoints across 110 providers) for the endpoints that do a job, e.g.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
jobstringrequired“What you want to do, in English or Korean.”limitinteger“Endpoints to return.”
- export_workflow
“36 step-by-step expert workflows for the export jobs around the data — what exporters usually learn too late: export readiness check (blind spots, 90-day plan), certification and registration in each…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
filestring“Optional, with name: a reference file the workflow mentions, e.g.”jobstring“What the user wants done, in their own words and any language (e.g.”namestring“A workflow name (from the list, or a name a TradeGraph answer mentions such as certification-check).”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-01.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 100% of 91
- Tools with a description
- 100% of 16
- Typical description length
- 1,115 characters
The tool set
Counted from the listing
- Tools
- 16
- Size of the list
- about 11,601 tokens for an agent to load (characters ÷ 4)
- Naming
- 16 of 16 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 16 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-01 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://tradegraph.rinda.ai/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"tradegraph": {
"url": "https://tradegraph.rinda.ai/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"tradegraph": {
"type": "http",
"url": "https://tradegraph.rinda.ai/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"tradegraph","type":"http","url":"https://tradegraph.rinda.ai/mcp"}'Claude Code
claude mcp add --transport http tradegraph https://tradegraph.rinda.ai/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"tradegraph": {
"type": "streamableHttp",
"url": "https://tradegraph.rinda.ai/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"tradegraph": {
"httpUrl": "https://tradegraph.rinda.ai/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.tradegraph] url = "https://tradegraph.rinda.ai/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"tradegraph": {
"url": "https://tradegraph.rinda.ai/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://tradegraph.rinda.ai/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint tradegraph.rinda.ai/mcp | Session opened | matches | our test · 2026-11-01 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-01 |
| Repository github.com/FINGU-GRINDA/tradegraph | Opens publicly | matches | api.github.com · 2026-11-01 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- ai.rinda.tradegraph
- GitHub owner
- an organization (FINGU-GRINDA)
- Repository
- github.com/FINGU-GRINDA/tradegraph
- Stars
- 0
- Repository age
- 0–30 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)
Source: the registry entry and api.github.com · 2026-11-01; security policy read from GitHub · 2026-11-01.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Tool list changes
Our reads compared · no tool calledHosted endpoint tradegraph.rinda.ai/mcp
No change in the tool list across 2 reads (2026-10-30 to 2026-11-01; versions 1.5.0 to 1.7.0).
Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-01 is not known yet. No tool was called. How it is compared
Choosing
Record checks
Public records · not a safety rating4 of 5 record checks met · 4 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 0 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.What changes this check: GitHub's documentation describes adding a SECURITY.md from the repository's security settings: under Reporting, Security policy, Start setup. GitHub: adding a security policy
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-01 (security policy 2026-11-01). No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about ai.rinda.tradegraph/tradegraph
Answered from the data aboveWho publishes ai.rinda.tradegraph/tradegraph?
The registry ties the namespace ai.rinda.tradegraph to the domain tradegraph.rinda.ai; only its owner can publish under it. Its linked repository is github.com/FINGU-GRINDA/tradegraph; GitHub reports its owner as FINGU-GRINDA, an organization. These are facts from the registry and GitHub, not a rating.
Is ai.rinda.tradegraph/tradegraph safe to install?
We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does ai.rinda.tradegraph/tradegraph need an API key or sign-in?
It opened a session without any credential on 2026-11-01. The registry entry declares no required credential; no declaration is not a guarantee.
Has ai.rinda.tradegraph/tradegraph been security tested?
Partly. 5 of the 16 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.
Does ai.rinda.tradegraph/tradegraph publish a security policy?
We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.
Where is the source code of ai.rinda.tradegraph/tradegraph?
In github.com/FINGU-GRINDA/tradegraph, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (we call no server's tools)
We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: exercised
- Fake assistant turns: exercised
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
5 exercised11 not run (reason given)2 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 5 of the 16 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised - 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
Source: our own test, 2026-11-01, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,117 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 16 tools, 1 resource, 11 prompts.
- 7,857 msFinished: 5 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “ai.rinda.tradegraph/tradegraph: MCP server record.” Data checked 2026-11-01. https://protocolprobe.com/mcp/servers/ai.rinda.tradegraph/tradegraph
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/ai.rinda.tradegraph/tradegraph)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology