MCP servers › io.github.Thorium › fuuga
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.Thorium/fuuga
Offline local-LLM helper: delegate simple errands to a local model, with sandboxed file tools. — the publisher's description
Summary
io.github.Thorium/fuuga is a local MCP server listed in the official MCP registry at version 1.0.41. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 4 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 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)
- 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- not applicable: The version the registry lists can be installed and is not withdrawn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: not an npm or PyPI package
- 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
- NuGet
- Tools
- 4
- Described as changing data
- 1 of 4 toolsAI-classified
- Mainly works on
- files and code on the machine it runs onAI-classified
- Topic
- ai-and-mlAI-classified
- Last tested
- 2026-10-23
Worth knowing before you connect it
- 1 tool is described as changing something (fuuga_delegate): our AI model's reading of the descriptions, not something we tested. We did not call it.
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
- 1.0.41, published 2026-10-14 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-14 (earliest version still in the registry; older removed versions would be earlier)
- 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 1.0.41 (published 2026-10-14).
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: files and code on the machine it runs on.
1 of 4 tools are described as changing something (creating, editing, deleting, sending or running).
- fuuga_delegateruns code or commandsdescribed as changing data
“Delegate a small, well-scoped errand to the local Fuuga minion.”
3 inputs, 1 required
taskstringrequired“The errand to carry out”filesarray“Optional workspace files to load as context”max_stepsinteger“Max tool-call rounds (default 8)”
“Read a UTF-8 text file from the workspace and return its contents.”
1 input, 1 required
pathstringrequired“Workspace-relative or absolute path to the file”
“List the files and subdirectories of a directory in the workspace.”
1 input
pathstring“Workspace-relative or absolute directory path.”
“Search workspace files for lines matching a regular expression.”
3 inputs, 1 required
patternstringrequired“Regular expression to search for”pathstring“Directory or file to search under.”globstring“Optional filename glob filter, e.g.”
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
- 100% of 4 tools
- Says what it returns
- 100% of 4 tools
- States limits, defaults or errors
- 25% of 4 tools
- Says when to use it
- 25% of 4 tools
- Items covered per tool
- 2.5 of 4 on average
Counted from the listing
- Parameters with a description
- 100% of 8
- Tools with a description
- 100% of 4
- Typical description length
- 136 characters
The tool set
Counted from the listing
- Tools
- 4
- Size of the list
- about 434 tokens for an agent to load (characters ÷ 4)
- Naming
- 3 of 4 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 4 of 4 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
- No config: no ready-made command for the NuGet package; use the publisher's instructions.
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.
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 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: not an npm or PyPI package
- 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.
- Does not applyPackage names its licence with a standard (SPDX) identifierNot an npm or PyPI package.
- Does not applyThe version the registry lists can be installed and is not withdrawnNot an npm or PyPI package.
- Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
- Does not applyNo known critical or high advisory in the package or its dependenciesNot an npm or PyPI package.
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.Thorium/fuuga
Answered from the data aboveIs io.github.Thorium/fuuga safe to install?
We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 1 of its tools describes 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.Thorium/fuuga 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.Thorium/fuuga do?
It lists 4 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 and run code or commands. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.Thorium/fuuga change or delete data?
1 of its tools says in its description that it creates, edits, deletes, sends or runs something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
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.Kastalien-Research/thoughtboxalso has tools that runs code or commands, reads or searchescompare with this one
- io.github.ariffazil/arifosarifOS — Constitutional AI Kernelalso has tools that runs code or commands, reads or searchescompare with this one
- io.github.DollhouseMCP/mcp-serverDollhouseMCPalso has tools that runs code or commands, reads or searchescompare with this one
- io.github.skynetcmd/m3-memoryM3 Memoryalso has tools that runs code or commands, reads or searchescompare with this one
- io.github.memtomem/memtomemalso has tools that runs code or commands, reads or searchescompare with this one
- io.github.michael-denyer/hot-memory-mcpalso has tools that runs code or commands, reads or searchescompare with this one
Active servers whose topic is also “ai-and-ml” 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)
- 18,677 msConnected after 0 redirects.
- Read the inventory: 4 tools, 0 resources, 0 prompts.
- 19,197 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.Thorium/fuuga: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.Thorium/fuuga
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.Thorium/fuuga)
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