MCP servers › io.github.Noshadi-sec › irp
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.Noshadi-sec/irp
Turn a research paper into working code and prove, claim by claim, how close it gets. — the publisher's description
Summary
io.github.Noshadi-sec/irp is a local MCP server listed in the official MCP registry at version 0.6.0. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 17 tools, 0 resources and 2 prompts.
Record checks
7 of 8 record checks met · 1 does 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
- met: 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- met: The version the registry lists can be installed and is not withdrawn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 applicable: npm package carries build provenance (attestation)
- not met: No known critical or high advisory in the package or its dependencies
- #14,745 of 15,112 packages by monthly downloads, tied with 367 others
- 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?
Key facts
- Runs
- local package
- Transport
- standard input/output
- Package
- PyPI · listed version current
- License
- MIT
- Dependencies
- 4 critical, 23 high advisories
- Repository
- public
- Tools
- 17
- Described as changing data
- 10 of 17 toolsAI-classified
- Mainly works on
- files and code on the machine it runs onAI-classified
- Topic
- developer-toolsAI-classified
- Last tested
- 2026-10-23
Worth knowing before you connect it
- 10 tools are described as changing something (fetch_paper, add_claim, add_guess, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
- 4 critical and 23 high advisories in its dependencies (as resolved on 2026-10-23).
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
- 0.6.0, published 2026-10-21 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-21 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 2 versions listed, all on 2026-10-21; 2 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 2 versions
0.6.0· 2026-10-210.5.0· 2026-10-21
- 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 0.6.0 (published 2026-10-21).
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.
10 of 17 tools are described as changing something (creating, editing, deleting, sending or running). For 1 the reading was uncertain, so no mark is shown.
- fetch_papercreates or changes datadescribed as changing data
“Create the study directory and fetch the paper into it: arXiv LaTeX source first (exact equations), the PDF as fallback and for page images.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 2 required
studystringrequired“Absolute path of the study directory.”paperstringrequired“arXiv ID or URL (e.g.”preferstring“Read LaTeX source when it exists (exact equations), else the PDF.”parserstring“PDF text parser when no LaTeX is used.”with_pdfboolean“Also download the PDF so get_page_image can show figures, tables and equations.”
“Read part of the paper with its original file and line numbers: a section, a table, figure, equation or algorithm, a LaTeX label, the abstract, a PDF page, a line range, or 'index' for the full outli…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 2 required
studystringrequired“Absolute path of the study directory.”idstringrequired“What to read: a section id ('sec:3', 'sec:3.2'), an item id ('tab:2', 'fig:1', 'eq:4', 'alg:1'), a LaTeX label ('eq:loss'), a section title, 'abstract', 'index…”offsetinteger“Skip this many lines of the selection (paging).”max_linesinteger“Return at most this many lines.”
“Render one page of the paper PDF as a PNG image, for equations, figures and tables that text extraction loses.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
studystringrequired“Absolute path of the study directory.”pageintegerrequired“1-based page number of the paper PDF.”dpiinteger“Rendering resolution; raise it for small math.”
“Record one number the paper claims, before writing any code (rule 5): the metric, the value as printed, where it appears and the success bar.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
16 inputs, 5 required
studystringrequired“Absolute path of the study directory.”statementstringrequired“Short name of the claim, e.g.”metricstringrequired“Metric name, e.g.”valuestringrequired“The paper's number exactly as printed, e.g.”wherestringrequired“Where the claim appears, as a reader would say it: 'Table 2, row 3', 'Figure 4', 'Section 5.2'.”where_kindstring“Kind of place the claim appears.”source_filestring or null“Paper file of the printed value, as get_section shows it (e.g.”source_lineinteger or null“Line of the printed value in source_file.”pageinteger or null“PDF page where the claim appears, if known.”comparatorstring“'approx' for 'about this value', 'at_least' for lower bounds such as speed-ups, 'at_most' for upper bounds such as error rates.”tolerance_relnumber or null“Reproduced if within this fraction of the paper's value (0.01 = 1%).”tolerance_absnumber or null“Reproduced if within this absolute difference.”close_relnumber or null“Close if within this fraction.”close_absnumber or null“Close if within this absolute difference.”seeds_in_paperinteger or null“Runs or seeds the paper averaged over, if stated.”notesstring or null“Anything a reader should know about this claim.”
“List every recorded claim with its success bar and current verdict.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
studystringrequired“Absolute path of the study directory.”
- add_guesscreates or changes datadescribed as changing data
“Record a detail the paper left out, the choice made and why (rule 2: never change the method to make a run succeed; record a guess instead).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 4 required
studystringrequired“Absolute path of the study directory.”missingstringrequired“The detail the paper left out, e.g.”choicestringrequired“What was chosen, e.g.”whystringrequired“Why, e.g.”sourcestring or null“Where the choice comes from: a citation, a URL or 'common default'.”claimsarray“Claim ids this guess can affect.”
- map_methodcreates or changes datadescribed as changing data
“Link an equation or algorithm step in the paper to the file and line in code/ that implements it.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 4 required
studystringrequired“Absolute path of the study directory.”paper_elementstringrequired“The paper element, e.g.”paper_refstring or null“Index id or LaTeX label of that element, e.g.”code_filestringrequired“File inside the study's code/ directory, e.g.”code_lineintegerrequired“First line that implements the element.”end_lineinteger or null“Last line, when the implementation spans several.”notestring or null“Why this line implements the element, if not obvious.”
“Build a pinned environment for the study's code: a uv virtual environment (fast, not a sandbox) or a Docker image (isolated).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
9 inputs, 1 required
studystringrequired“Absolute path of the study directory.”namestring“Environment name; never reused.”backendstring“'uv' builds a virtual environment (not a sandbox); 'docker' builds an image runs are isolated in.”pythonstring“Python version, e.g.”requirementsstring or null“Requirements file inside code/.”packagesarray“Extra packages, e.g.”base_imagestring or null“Docker base image; default python:<python>-slim.”system_packagesarray“Debian packages for the Docker image.”gpuboolean“Docker runs request all GPUs (--gpus all).”
“Run one command in code/ with the named environment.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
12 inputs, 2 required
studystringrequired“Absolute path of the study directory.”commandstringrequired“Shell command to run inside the environment, e.g.”envstring or null“Environment from create_env; null uses the host environment (no lock file).”scopestring“'full' is the faithful configuration and is the only scope that can count; 'shortened' (fewer steps or data) and 'smoke' never count.”seedinteger or null“Seed, passed as IRP_SEED and PYTHONHASHSEED and recorded.”cwdstring“Working directory inside code/.”timeout_sinteger“Stop the run after this many seconds.”waitboolean“Wait for the run to finish.”networkboolean“Docker only: allow network access during the run.”memory_limitstring or null“Docker only: memory cap such as '8g'.”commitboolean“Commit code/ to git before the run so the report names the exact code.”notestring or null“What this run is for, shown in the report.”
“Report a run's status, exit code and the last lines of its output; optionally wait for it to finish.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 2 required
studystringrequired“Absolute path of the study directory.”run_idstringrequired“Run id, e.g.”wait_sinteger“Wait up to this many seconds for the run to finish.”tail_linesinteger“Lines of stdout and stderr to return.”
- run_remotedescribed as changing data
“Run one command on a paid GPU provider (Modal today; RunPod and Hugging Face Jobs planned).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
13 inputs, 4 required
studystringrequired“Absolute path of the study directory.”commandstringrequired“Shell command to run in the remote sandbox.”envstring“Environment whose requirements and Python version the sandbox uses.”providerstring“Compute provider.”gpustringrequired“GPU type, e.g.”gpu_countinteger“Number of GPUs; multiplies the estimate.”hoursnumberrequired“Time limit in hours; also the basis of the cost estimate.”approvedboolean“Set true only after showing the person the cost estimate and receiving their approval.”scopestring“'full' is the only scope that can count; see run.”seedinteger or null“Seed, passed as IRP_SEED and recorded.”outputsarray“Files under code/ to copy back after the run.”waitboolean“Wait for completion; remote runs usually outlast tool timeouts.”notestring or null“What this run is for, shown in the report.”
- extract_metricsreads or searches
“Pull numbers from a completed run's stdout, stderr or the files it wrote, by key, regex, JSON pointer or CSV column.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 3 required
studystringrequired“Absolute path of the study directory.”run_idstringrequired“Completed run to read, e.g.”specsarrayrequired“One spec per number to extract.”
Show 5 more tools
“Put a claim beside its measurements and record one of four verdicts: reproduced, close, not reproduced, or could not run.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
10 inputs, 2 required
studystringrequired“Absolute path of the study directory.”claim_idstringrequired“Claim to judge, e.g.”measurement_idsarray“Measurements from extract_metrics, one per seed or run; their mean is compared.”unit_scalenumber“Power of ten to convert units, e.g.”could_not_runboolean“Record 'could not run' instead of a measured verdict.”reasonstring or null“Could not run: short reason, e.g.”blocking_errorstring or null“Could not run: the exact blocking error or constraint.”failed_run_idstring or null“Could not run: the run that failed, if any.”context_measurement_idsarray“Measurements shown for context that do not count, e.g.”notestring or null“Context for the verdict, shown in the report.”
“Record a limitation, a forced deviation from the paper, something not checked, or an author contact.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
studystringrequired“Absolute path of the study directory.”kindstringrequired“limitation, deviation (a forced change from the paper), not_checked, author_contact or other.”textstringrequired“The note itself, in plain words.”claimsarray“Claim ids the note concerns.”
“Write report.md and report.json from the evidence log only: claim table, verdicts, guesses, method map and provenance.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 1 required
studystringrequired“Absolute path of the study directory.”draftboolean“Write report.draft.md/json even if the completion gate has not passed.”bundlestring or null“Absolute path of a new directory to receive a shareable bundle (report, evidence, code, locks, logs; never the paper PDF or source).”
“Recheck the evidence log's hash chain and the hash of every recorded file; reports each problem.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
studystringrequired“Absolute path of the study directory.”
- study_statusreads or searches
“Show the study at a glance: paper, claims and verdicts, guesses, environments, runs, and what still blocks a final report.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
studystringrequired“Absolute path of the study directory.”
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 2026-10-23.
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 17 tools
- Says what it returns
- 75% of 16 tools
- States limits, defaults or errors
- 18% of 17 tools
- Says when to use it
- 18% of 17 tools
- Items covered per tool
- 2.1 of 4 on average
Counted from the listing
- Parameters with a description
- 100% of 102
- Tools with a description
- 100% of 17
- Typical description length
- 190 characters
The tool set
Counted from the listing
- Tools
- 17
- Size of the list
- about 6,745 tokens for an agent to load (characters ÷ 4)
- Naming
- 13 of 17 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 17 of 17 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 PyPI package irp-agents
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": {
"irp": {
"command": "uvx",
"args": [
"irp-agents==0.6.0",
"mcp"
]
}
}
}Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"irp": {
"command": "uvx",
"args": [
"irp-agents==0.6.0",
"mcp"
]
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"irp": {
"type": "stdio",
"command": "uvx",
"args": [
"irp-agents==0.6.0",
"mcp"
]
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"irp","type":"stdio","command":"uvx","args":["irp-agents==0.6.0","mcp"]}'Claude Code
claude mcp add --transport stdio irp -- uvx irp-agents==0.6.0 mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- uvx irp-agents==0.6.0 mcp
- Arguments are written as the registry entry gives them; a named one as “--name value”, the form the registry documentation shows.
- This runs the publisher's code on your machine (uvx). 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
- 0.6.0
- Latest stable
- 0.6.0
- Status
- current
- Withdrawn
- no
Source: pypi.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 (OSV.dev). Bars share one scale. The package itself has no known vulnerability (OSV.dev).
Integrity, provenance, license
- Integrity
- sha256-74baa18c12e74ce47…
- License
- MIT
Source: the package registry · 2026-10-23.
Usage
- Downloads
- 0 in the last month
Source: pypistats.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 0.6.0 on PyPI | Exists and can be installed | matches | PyPI · 2026-10-23 |
| Repository github.com/Noshadi-sec/irp | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.Noshadi-sec
- GitHub owner
- a personal account (Noshadi-sec)
- Repository
- github.com/Noshadi-sec/irp
- Stars
- 0
- Repository age
- 0–30 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- SECURITY.md
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
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.
Choosing
Record checks
Public records · not a safety rating7 of 8 record checks met · 1 does not apply
- #14,745 of 15,112 packages by monthly downloads, tied with 367 others
- 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.
- MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
- MetPackage names its licence with a standard (SPDX) identifierMIT
- MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
- Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
- Not metNo known critical or high advisory in the package or its dependencies27 critical or high advisories in its dependencies.
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.Noshadi-sec/irp
Answered from the data aboveIs io.github.Noshadi-sec/irp safe to install?
We do not rate servers as safe or unsafe. 7 of its 8 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. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has advisories (4 critical, 23 high and 12 moderate; OSV.dev). 10 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.Noshadi-sec/irp been security tested?
Partly. 4 of the 13 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.Noshadi-sec/irp do?
It lists 17 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, run code or commands and generate content. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.Noshadi-sec/irp change or delete data?
10 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.
Does io.github.Noshadi-sec/irp publish a security policy?
Yes: its repository has a public security policy (github.com/noshadi-sec/irp/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.
Is the listed version current?
Yes. The registry lists 0.6.0, the latest stable release on PyPI.
Where is the source code of io.github.Noshadi-sec/irp?
In github.com/Noshadi-sec/irp, 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.
Similar servers
Same topic · AI-read
- io.github.tomyud1/godot-mcpalso has tools that creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
- io.github.Keesan12/martin-loopMartin Loopalso has tools that creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
- io.github.IMNMV/clauderClaudeR - RStudio MCP Serveralso has tools that creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
- io.github.SummerEngine/summerSummer Enginealso has tools that creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
- io.github.SupportPages-io/wtfmWTFMalso has tools that creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
- io.github.mybolide/mcp-probe-kitalso has tools that creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
Active servers whose topic is also “developer-tools” 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: exercised
- Fake assistant turns: exercised
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not applicable
- Consent handling: not applicable
- Sign-in metadata: not applicable
4 exercised9 not run (reason given)5 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 13 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
- 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
- 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)
- 4,513 msConnected after 0 redirects.
- Read the inventory: 17 tools, 0 resources, 2 prompts.
- 5,031 msFinished: 4 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.Noshadi-sec/irp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.Noshadi-sec/irp
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.Noshadi-sec/irp)
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