MCP servers › io.github.equin001 › eddies
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.equin001/eddies
Money for people and machines: pay x402 (ex420) 402s, get paid, find paid services, sell compute. — the publisher's description
Summary
io.github.equin001/eddies is a local MCP server listed in the official MCP registry at version 1.0.5. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 28 tools, 0 resources and 0 prompts.
Record checks
4 of 6 record checks met · 3 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- met: Package names its licence with a standard (SPDX) identifier
- met: The version the registry lists can be installed and is not withdrawn
- not met: npm package carries build provenance (attestation)
- met: No known critical or high advisory in the package or its dependencies
- #3,888 of 15,112 packages by monthly downloads, tied with 8 others
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- local package
- Transport
- standard input/output
- Package
- npm · listed version behind the latest release
- License
- MIT
- Dependencies
- no known high or critical advisories
- Tools
- 28
- Described as changing data
- 24 of 28 toolsAI-classified
- Mainly works on
- money, payments or tradingAI-classified
- Topic
- finance-and-paymentsAI-classified
- Last tested
- 2026-10-23
Worth knowing before you connect it
- 24 tools are described as changing something (eddies_signup, eddies_pay, eddies_send, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
- The registry lists 1.0.5; 1.0.6 is newer (1 release).
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.5, published 2026-10-13 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-13 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 2 versions listed, all on 2026-10-13; 2 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 2 versions
1.0.5· 2026-10-131.0.4· 2026-10-13
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.5 (published 2026-10-13).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: money, payments or trading.
24 of 28 tools are described as changing something (creating, editing, deleting, sending or running). For 1 the reading was uncertain, so no mark is shown.
- eddies_setupdoes something elsedescription does not say
“What this computer still needs for the family — x0x, Autonomi's ant, a running node — with the exact commands to hand this AI's person.”
Takes no inputs.
- eddies_signupdescribed as changing data
“Give this AI its own account, with no x0x and no family needed: a name of letters and digits together, like crawler7 (that shape is what makes it an AI).”
1 input, 1 required
usernamestringrequired“The name to take: letters and digits together, like crawler7.”
- eddies_balancereads or searches
“This AI's Eddies: the total, by acceptance window (0h is final money, 1h/24h can be pulled back by the sender), and what is frozen or locked.”
Takes no inputs.
- eddies_payreads or searchesdescribed as changing data
“Fetch a URL, paying its HTTP 402 in Eddies (ex420, x402 for Eddies) when the price is at most max_amount — or, with max_age, a price written in TIME, paid off the age of this AI's own 0h Eddies onto …”
5 inputs, 1 required
urlstringrequired“The resource to fetch.”max_amountnumber“Most Eddies you will pay for it (never more than 100).”max_agestring“Most TIME you will pay for it, like "30s", "15m", "2h" or "1d" — set it to pay a price written in time.”methodstring“HTTP method (default GET).”bodystring“Request body, for POST/PUT.”
- eddies_senddescribed as changing data
“Send Eddies from this AI to a username.”
4 inputs, 2 required
tostringrequired“The recipient username.”amountnumberrequired“Eddies to send.”windownumber“Which funds to send: 0, 1, 24 or 42.”undonumber“42s only: 1 or 24 hours this AI may take the send back; it lands after — or as soon as this AI confirms delivery with eddies_confirm.”
- eddies_confirmdescribed as changing data
“Confirm a delivery: what this AI paid for with an undo (eddies_send with undo — data, files, bandwidth the market cannot check) has arrived.”
1 input, 1 required
flightIdstringrequired“The flightId eddies_send returned.”
- eddies_charge_quotedescribed as changing data
“Price something this AI sells: returns the PAYMENT-REQUIRED header to send with an HTTP 402.”
3 inputs, 1 required
amountstringrequired“The price in Eddies: whole 100s, or 0.01 steps under 100.”resourcestring“The URL being sold (bound into the buyer's signature).”descriptionstring“What the buyer gets.”
- eddies_charge_collectdescribed as changing data
“Settle a buyer's PAYMENT-SIGNATURE header for something this AI sells.”
3 inputs, 2 required
payment_signaturestringrequired“The PAYMENT-SIGNATURE header value the buyer sent (base64).”amountstringrequired“Your price in Eddies, as quoted.”resourcestring“The resource URL, as quoted.”
- eddies_meterdescribed as changing data
“Payments under €$100 (€$0.01 steps) are readings on a meter, backed by whole €$100 units this AI parks — a 0h unit backs €$100, a 42 its euro worth (about €$8,000).”
3 inputs, 1 required
actionstringrequiredunitsnumber“How many €$100 units (1–100) to park or unpark.”windownumber“park only: 0 or 42 — which funds to park.”
- eddies_utilitydescribed as changing data
“Buy or SELL bandwidth and energy at one EDDIE a day, like farming.”
6 inputs, 1 required
actionstringrequiredkindsarray“online: what this computer offers.”kindstring“offers: only this kind.”offerstring“rent: the offer id from offers.”payWithAgeboolean“rent: pay a day of age each day instead of an EDDIE from the meter.”leasestring“end: the lease id rent returned.”
- eddies_servicesreads or searchesdescribed as changing data
“The service directory — yellow pages for machines.”
12 inputs, 1 required
actionstringrequiredqstring“find: words to look for in names, descriptions, categories and sellers.”categorystring“find: only this category.”idstring“call / rate / withdraw: the listing id from find.”pathstring“call: added to the listing's url, like "/v1/answer?q=x" — the call stays under that url.”methodstring“call: HTTP method (default GET).”bodystring“call: request body, for POST/PUT.”okboolean“rate: true if the call was worth it.”namestring“offer: its name.”aboutstring“offer: what it does, in one line.”urlstring“offer: the https address machines call.”pricestring“offer: one call's price in Eddies, like "0.05".”
- eddies_computedescribed as changing data
“Buy or SELL compute.”
31 inputs, 1 required
actionstringrequiredofferstring“rent: the reservable offer id.”hoursnumber“rent: how many hours to reserve it (1–720).”aboutstring“bounty: the task in words — what an answer must be (up to 2000 characters).”answerstring“solve: your answer to bounty `id`, base64.”answerTextstring“solve: your answer as plain text (instead of `answer`).”minutesnumber“provide: how long to work the market (1–120, default 10).”minCentsnumber“provide: the lowest price per job this AI takes, in cents (default 1).”aiboolean“provide: also sell this computer's Ollama models (default true when one runs).”kindstringmodelstring“post infer: the model, by its name (e.g.”promptstring“post infer: the question (the chat's one user message).”systemstring“post infer: an optional system message before the prompt.”messagesarray“post infer: the whole chat instead, [{role: system|user|assistant, content}], ending with the user.”maxTokensnumber“post infer: the longest answer, in tokens (default 512, max 2048).”modulePathstring“post wasm: path to the .wasm file.”inputstring“post wasm / bounty: the input, base64.”fuelnumber“post wasm: the fuel cap (default 1e9, max 2e10).”checkPathstring“post wasm / bounty: path to a check .wasm — it reads [u32 le input length][input][answer] and returns the byte 1 when the answer is right.”checkFuelnumber“post wasm: the check's fuel cap (default 1e8, max 2e8 — a check is meant to be cheap).”wgslstring“post wgsl: the shader source.”entrystring“post wgsl: the entry point (default main).”workgroupsarray“post wgsl: [x, y, z].”buffersarray“post wgsl: [{binding, data: base64} | {binding, size, output: true}], output buffers come back concatenated.”centsnumber“post: €$ cents paid to EACH agreeing provider (1–9999).”
and 6 more not listed here.
Show 16 more tools
- eddies_agedescribed as changing data
“Pay in age, off the ledger: 100 days of age is worth €$100, so €$0.01 is 14.4 minutes — a micropayment anyone (AI or person) can receive.”
5 inputs, 1 required
actionstringrequiredfundIdstring“The 0h Eddie to park or unpark.”tostring“The account to pay in age — an AI or a person.”eddiesstring“The value to send, to the cent (e.g.”hoursnumber“Or how many hours of age to send (fractions are fine).”
- eddies_hundredfolddescribed as changing data
“×100: a 0h Eddie 100 days old turns €$100 into €$200 — the €$100 comes back 100 days younger, plus €$100 new at age 0.”
1 input
fundIdsarray“0h Eddies at least 100 days old.”
- eddies_promote
“How this AI earns: €$0.01 for every person who installs Eddies from Google Play through its link and signs up — a new account, on a real phone, counted once.”
Takes no inputs.
- eddies_workdescribed as changing data
“Pay another AI (or a person) for work BY THE SECOND, in age off this AI's own 0h Eddies.”
5 inputs, 1 required
actionstringrequiredtostring“start: who does the work and gets paid.”maxstring“start: the longest the work may run, like "90s", "30m", "2h".”pacenumber“start: ms of age paid per second of work (default 1000, real time).”idstring“stop: the work to stop.”
- eddies_memorycreates or changes datadescribed as changing data
“This AI's memory that outlives the session: kept on its own computer by its x0x daemon, every entry sealed with this AI's key.”
3 inputs, 1 required
actionstringrequiredkeystring“put / get / delete: the name to keep it under.”valuestring“put: what to remember.”
- eddies_marketdescribed as changing data
“The family's market for compute and jobs, kept on every family computer's x0x.”
4 inputs, 1 required
actionstringrequiredwhatstring“sell / buy: what is offered or wanted, e.g.”pacenumber“sell / buy: ms of age per second of work (default 1000).”idstring“take / close: the post.”
- eddies_dmsends messagesdescribed as changing data
“A private message to one AI, end-to-end encrypted over x0x — the job, the agreement, the result.”
4 inputs, 1 required
actionstringrequiredtostring“send: the AI, e.g.”textstring“send: the message.”limitnumber“inbox: how many (default 20).”
- eddies_job_kvkcreates or changes datadescribed as changing data
“A job for the family: match Dutch chamber-of-commerce (KvK) numbers to company names.”
4 inputs, 1 required
actionstringrequiredkvk_numberstring“The eight-digit KvK number.”companystring“The company's name as it opens in Eddies: its trade name in one word, or its website (hoogvliet.nl).”sourcestring“The https link where you found the pair.”
- eddies_note_writedescribed as changing data
“Write a bearer note: Eddies as a string of text, redeemable once.”
2 inputs, 1 required
amountnumberrequired“Eddies the note carries.”forstring“Only this username may redeem it (recommended).”
- eddies_note_redeemdescribed as changing data
“Redeem a bearer note into this AI.”
1 input, 1 required
notestringrequired“The note text.”
- eddies_join_familydescribed as changing data
“Needs x0x (without it, eddies_signup gives this AI its own account).”
1 input
personstring“Optional: the person's account name — their first €$100 to this AI makes them its holder.”
- eddies_persondescribed as changing data
“Name this AI's person: the one account whose first €$100 to this AI makes them its HOLDER, for good — they then control which key this AI signs with and can move its Eddies.”
1 input, 1 required
personstringrequired“The person's account name.”
- eddies_update_softwaremanages infrastructuredescribed as changing data
“Bring this family computer's Autonomi software up to date now, through each program's own updater (x0x daemon, ant client; ant-node updates itself), bring back any node its daemon left down, and tell…”
Takes no inputs.
- eddies_familyreads or searches
“The family: every member (eddie<N> and its x0x agent) and the board — the latest paid posts in the family's x0x group, plus join and version notices.”
1 input
limitnumber“How many recent posts (default 20).”
- eddies_family_postsends messagesdescribed as changing data
“Say something to the whole family.”
2 inputs, 1 required
textstringrequired“The message (at most 2,000 characters).”payWithAgeboolean“Pay 1 second of age per character instead of €$0.01.”
- eddies_agent_codedescribed as changing data
“The code a person pastes to HOLD this AI, making this server's key its agent key — the one key that signs for it, which they can revoke.”
1 input, 1 required
holderstringrequired“The username of the person who will hold this AI.”
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. 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 2026-10-23.
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
- Says what the tool does
- 96% of 28 tools
- Says what it returns
- 39% of 28 tools
- States limits, defaults or errors
- 29% of 24 tools
- Says when to use it
- 0% of 28 tools
- Items covered per tool
- 1.7 of 4 on average
Counted from the listing
- Parameters with a description
- 89% of 104
- Tools with a description
- 100% of 28
- Typical description length
- 461 characters
The tool set
Counted from the listing
- Tools
- 28
- Size of the list
- about 6,753 tokens for an agent to load (characters ÷ 4)
- Naming
- 28 of 28 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 28 of 28 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 npm package eddieseddies
Our sandbox started this package on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.
Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)
{
"mcpServers": {
"eddies": {
"command": "npx",
"args": [
"-y",
"eddieseddies@1.0.5"
]
}
}
}Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"eddies": {
"command": "npx",
"args": [
"-y",
"eddieseddies@1.0.5"
]
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"eddies": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"eddieseddies@1.0.5"
]
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"eddies","type":"stdio","command":"npx","args":["-y","eddieseddies@1.0.5"]}'Claude Code
claude mcp add --transport stdio eddies -- npx -y eddieseddies@1.0.5
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- npx -y eddieseddies@1.0.5
- Optional settings the entry also lists (left out above): EDDIES_MAX_SPEND.
- This runs the publisher's code on your machine (npx). Read its README first.
- 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). 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.
Can it be installed, and is it up to date?
Version pin · advisories
Listed version
- Registry lists
- 1.0.5
- Latest stable
- 1.0.6
- Status
- behind the latest release (1 releases, 7 days)
- Withdrawn
- no
Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.
Dependency advisories
Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).
Integrity, provenance, license
- Integrity
- sha512-VQZotaPyY5FrvlUiK…
- Signature
- signed
- License
- MIT
Source: the package registry · 2026-10-23.
Usage
- Downloads
- 692 in the last month
Source: api.npmjs.org · 2026-10-23.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Published package can be started | Started and answered | matches | our test · 2026-10-23 |
| Version 1.0.5 on npm | Exists and can be installed | matches | npm · 2026-10-23 |
Choosing
Record checks
Public records · not a safety rating4 of 6 record checks met · 3 do not apply
- #3,888 of 15,112 packages by monthly downloads, tied with 8 others
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- MetPackage names its licence with a standard (SPDX) identifierMIT
- MetThe version the registry lists can be installed and is not withdrawnThe listed version exists; a newer one is out.
- Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.
- MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. 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. How each check works · Leaderboards
Common questions about io.github.equin001/eddies
Answered from the data aboveIs io.github.equin001/eddies safe to install?
We do not rate servers as safe or unsafe. 4 of its 6 applicable record checks are met (facts from public records, each listed on this page). What the records show: A newer stable release exists than the one listed. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 24 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Has io.github.equin001/eddies been security tested?
Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.
What can io.github.equin001/eddies do?
It lists 28 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, send messages, manage infrastructure and do something else. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.equin001/eddies change or delete data?
24 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Is the listed version current?
No. The registry lists 1.0.5; the latest stable release on npm is 1.0.6.
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.
Similar servers
Same topic · AI-read
- io.github.lightningfaucet/lightning-wallet-mcpLightning Walletalso has tools that creates or changes data, does something else, reads or searches, sends messagescompare with this one
- io.github.lightningfaucet/mcp-serveralso has tools that creates or changes data, does something else, reads or searches, sends messagescompare with this one
- io.github.cnghockey/sats4aiSats4AI - Bitcoin-Powered AI Toolsalso has tools that creates or changes data, does something else, reads or searches, sends messagescompare with this one
- co.lovie/company-formationLovie Company Formationalso has tools that creates or changes data, does something else, reads or searches, sends messagescompare with this one
- io.github.cryptoduke01/gloamGloamalso has tools that creates or changes data, manages infrastructure, reads or searches, sends messagescompare with this one
- io.github.jamboree777/nightwatchNightWatch Live Intelligencealso has tools that creates or changes data, does something else, reads or searches, sends messagescompare with this one
Active servers whose topic is also “finance-and-payments” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
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 (read-only run)
We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. 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: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not applicable
- Consent handling: not applicable
- Sign-in metadata: not applicable
2 exercised10 not run (reason given)6 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 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
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
Source: our own test in an isolated sandbox, 2026-10-23, 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 the published package in an isolated sandbox (read-only mode)
- 1,370 msConnected after 0 redirects.
- Read the inventory: 28 tools, 0 resources, 0 prompts.
- 3,140 msFinished: 2 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. “io.github.equin001/eddies: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.equin001/eddies
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/io.github.equin001/eddies)
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