Skip to content

MCP servers › fyi.levels › levels-fyi

MCP server · registry snapshot 2026-10-30 · last tested 2026-10-30

levels-fyi MCP server

Registry name fyi.levels/levels-fyi

by levels.fyi · domain (the registry's namespace rule)repository owner on GitHub: Levels-fyi (organization)Source ↗Website ↗

Salary, level and job data from 1M+ pay reports. Benchmark pay, evaluate offers, search open jobs. — the publisher's description

4 of 4 record checks metRead-only · tools listed 2026-10-30version 1.0.0JavaScriptstreamable HTTP30 tools

Summary

fyi.levels/levels-fyi is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain levels.fyi. Its linked repository is github.com/Levels-fyi/levels-fyi-plugin; GitHub reports its owner as Levels-fyi, an organization. On 2026-10-30 ProtocolProbe connected to it in read-only mode and read its inventory: 30 tools, 0 resources and 0 prompts.

Record checks

4 of 4 record checks met · 4 do not apply · 1 not checked

  • 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 checked: 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  • not applicable: The version the registry lists can be installed and is not withdrawn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
30
Last tested
2026-10-30

Tool list size

16,363 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (30 tools). Counted with Anthropic's token counter on 2026-10-30, from the tool list we read on 2026-10-30. 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 2026-10-30 (mcp.levels.fyi), 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 (1.0.0).

Add to your client

Observed fact

This server accepted a session without any credential and lists 3 tools whose name or declaration suggests they change data (upload-resume, add-salary-submission, send-feedback). That is our reading of the names; we did not call them. Source: our connection, 2026-10-30.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-30
Mode
read-only (no tool calls)
Latest version
1.0.0, published 2026-10-29 (registry, as of the 2026-10-30 snapshot)
First listed version
2026-10-29 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-10-30
Package and repository
checked 2026-10-30
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

New in the registry: not in the list of 2026-10-29, listed on 2026-10-30 with version 1.0.0 (published 2026-10-29).

Source: the official MCP Registry list on 2026-10-29 and on 2026-10-30.

What it is

What does this server offer?

Observed inventory
30tools
0resources
0prompts

None of its 30 tools are described as changing anything. For 30 the reading was uncertain, so no mark is shown.

  • get-permissions

    “Connectivity check for the Levels.fyi MCP server.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input
    • messagestring“Optional text to echo back in the response.”
  • get-salary-percentiles

    “Get the median (p50) yearly total compensation in USD for a job family in one location, across all levels, from submissions in the last 12 months.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 2 required
    • jobFamilySlugstringrequired“A Levels.fyi job family slug, e.g.”
    • locationSlugstringrequired“One location slug (metro, state, country or region; not a city), e.g.”
  • get-salaries-by-company-level

    “Get median (p50) yearly total compensation in USD for each of ONE company's internal levels (e.g.”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs, 3 required
    • jobFamilySlugstringrequired“A Levels.fyi job family slug, e.g.”
    • locationSlugstringrequired“One location slug (metro, state, country or region; not a city), e.g.”
    • companySlugstringrequired“A company slug, e.g.”
  • search-raw-data-points

    “Get the newest individual salary submissions for a job family, optionally narrowed to one location and/or one company.”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs, 1 required
    • jobFamilySlugstringrequired“A Levels.fyi job family slug, e.g.”
    • locationSlugstring“One location slug (city, metro, state, country or region), e.g.”
    • companySlugstring“A company slug, e.g.”
  • get-company

    “Look up a single company by its slug (preferred) or name, returning its full profile: name, slug, employee count, headquarters, founding year, ticker, company type, and estimated valuation.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • companyNameOrSlugstringrequired“Name or slug of a company”
  • get-company-levels

    “Get a company's INTERNAL level names for a job family, ordered by seniority (e.g.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 2 required
    • companySlugstringrequired“The company (slug) whose internal level structure to list, e.g.”
    • jobFamilySlugstringrequired“A Levels.fyi job family slug, e.g.”
  • get-company-group

    “Resolve a named company group (e.g.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input
    • groupstring“Company group name to resolve (e.g.”
  • search-companies

    “Search companies using searchText input (required) and get their Levels.fyi slugs.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 1 required
    • searchTextstringrequired“Company name to search for, current or former (e.g.”
    • limitnumber“Max results to return (1–15).”
  • search-companies-by-vesting

    “Find companies by their equity vesting characteristics: vesting/equity type (e.g.”

    Publisher declares: read-only yes · destructive no · open-world no

    6 inputs
    • vestingTypestring“Filter by vesting/equity type substring, e.g.”
    • vestingPatternstring“Filter by vesting shape: frontloaded, backloaded (e.g.”
    • minYearsnumber“Minimum total vesting years.”
    • maxYearsnumber“Maximum total vesting years.”
    • hasCliffboolean“Filter by whether the schedule has a 1-year cliff.”
    • limitnumber“Max companies to return (1–50).”
  • search-top-companies

    “Get the top-paying companies for a job family within one country, ranked by median (p50) yearly total compensation in USD.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 2 required
    • jobFamilySlugstringrequired“A Levels.fyi job family slug, e.g.”
    • countrySlugstringrequired“A COUNTRY location slug, e.g.”
  • get-locationon 1 other server

    “Look up one or more location slugs and get their details: name, type (country / metro-DMA / state), parent country, currency, and coordinates.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • locationSlugsarrayrequired“Location slug for the locations”
  • get-location-stats

    “Get the top-paying locations for a job family within one country, ranked by median (p50) yearly total compensation in USD from submissions in the last 2 years.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 2 required
    • jobFamilySlugstringrequired“A Levels.fyi job family slug, e.g.”
    • countrySlugstringrequired“A COUNTRY location slug, e.g.”
Show 18 more tools
  • search-locationson 1 other server

    “Search locations (countries, metro areas / DMAs, and US states) using searchText input (required) and get their Levels.fyi slugs.”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs, 1 required
    • searchTextstringrequired“Location name to search for (country, metro area / DMA, or US state).”
    • typestring“Restrict results to one location type.”
    • limitnumber“Max results to return (1–15).”
  • get-job-family

    “Look up a job family by its slug and get its focus areas (specializations) with their titles, plus untagged titles.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • jobFamilySlugstringrequired“A Levels.fyi job family slug, e.g.”
  • search-job-families

    “Search job families / roles using searchText input (required) and get their Levels.fyi slugs.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 1 required
    • searchTextstringrequired“Job family / role name to search for (e.g.”
    • limitnumber“Max results to return (1–15).”
  • search-job-titles

    “Search specific job titles by name.”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs, 1 required
    • searchTextstringrequired“Job title to search for (e.g.”
    • limitnumber“Max results to return (1–15).”
    • excludeFamilyLikeTitlesboolean“When true, exclude titles that are effectively the same as their job family.”
  • search-focus-areas

    “Search focus tags (specializations within a role, e.g.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 1 required
    • searchTextstringrequired“Focus tag / specialization name to search for (e.g.”
    • limitnumber“Max results to return (1–15).”
  • search-role-terms

    “Resolve a role term by searching job families, job titles, and focus tags TOGETHER in one call.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 1 required
    • searchTextstringrequired“Role term to resolve across job families, titles, and focus tags.”
    • limitnumber“Max results to return (1–15).”
  • “Get the signed-in user's own Levels.fyi career profile: current title, company, career level, job family, focus area, location, years of experience, skills, certifications and work history, plus the …”

    Publisher declares: read-only yes · destructive no · open-world no

    Takes no inputs.

  • upload-resume

    “Add or replace the signed-in user's resume on Levels.fyi.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • fileTypestringrequired“The resume file's format: "pdf" or "docx".”
  • add-salary-submission

    “Add the user's own compensation to Levels.fyi: pay they earn now or a job offer they received.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    36 inputs, 7 required
    • companySlugstring“The company slug from search-companies.”
    • companyNamestring“The company name, only for a company that search-companies cannot find.”
    • jobFamilySlugstringrequired“A Levels.fyi job family slug, e.g.”
    • titlestringrequired“The job title as the user states it, e.g.”
    • levelstring“The company's own level name from get-company-levels, e.g.”
    • focusTagSlugstring“A focus area slug from get-job-family for this job family, e.g.”
    • teamstring“The team or organization within the company, e.g.”
    • locationSlugstringrequired“A CITY slug from search-locations with type "city".”
    • compensationPerspectivestringrequired“"offer" for a job offer the user received, "employee" for pay they earn now.”
    • sourceDatestring“YYYY-MM-DD.”
    • currencystringrequired“The currency of every amount in this submission, e.g.”
    • baseSalaryValuenumberrequired“The base salary per baseSalaryTimeUnit.”
    • baseSalaryTimeUnitstringrequired“The period baseSalaryValue is paid per, usually "yearly".”
    • totalStockGrantValuenumber“Offers only: the total value of the stock (RSU) grant over the whole vesting period.”
    • vestingSchedulearray“Offers only; required with totalStockGrantValue.”
    • avgAnnualStockGrantValuenumber“Employees only: the stock (RSU) value they receive per year.”
    • stockTypestring“"stock" for RSUs, "option" for stock options.”
    • totalOptionsGrantednumber“Offers only: the number of stock options in the whole grant.”
    • avgAnnualOptionsGrantednumber“Employees only: the number of stock options that vest per year.”
    • optionStrikePricenumber“With options: the exercise (strike) price per option.”
    • optionPreferredPricenumber“With options: the latest preferred share price, usually from the last funding round.”
    • optionPriceCurrencystring“The currency of optionStrikePrice and optionPreferredPrice, when it differs from currency (e.g.”
    • annualBonusValuenumber“The yearly bonus: for an offer the target bonus amount, for an employee the bonus they actually receive per year.”
    • annualTargetBonusPercentagenumber“Offers only: the target bonus as a percent of base, when stated that way.”
    • signOnBonusValuesarray“Offers only: the sign-on bonus, one amount per year it is paid, e.g.”

    and 11 more not listed here.

  • get-salary-submission-by-id

    “Get a single salary submission by its UUID: company, title, level, location, years of experience, offer date, base salary and total compensation.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • uuidstringrequired“The unique uuid of the salary”
  • get-vesting-schedules

    “Get equity vesting schedules for one or more companies, decoded into structured data: per-year vesting percent and frequency (cliff/quarterly/monthly), whether there's a 1-year cliff, whether it's ba…”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • companySlugsarrayrequired“Company slugs to fetch vesting schedules for.”
  • “Search open jobs on Levels.fyi, with the pay range each posting states.”

    Publisher declares: read-only yes · destructive no · open-world no

    13 inputs, 1 required
    • querystringrequired“Role names and terms that appear in job posts, e.g.”
    • locationSlugstring“One location slug from search-locations (city, metro, state or country).”
    • companySlugsarray“Company slugs from search-companies, at most 5.”
    • jobFamilySlugsarray“Job family slugs from search-job-families, at most 10.”
    • standardLevelsarray
    • workArrangementsarray
    • employmentTypesarray
    • postedWithinDaysnumber“Only jobs posted in the last N days.”
    • minBaseCompensationnumber“Minimum base salary, compared with the top of the posting's range as posted (most postings are USD).”
    • minMedianTotalCompensationnumber“Minimum total compensation, compared with the top of the posting's range.”
    • sortBystring
    • limitnumber“Companies per page (default 10, max 25).”
    • offsetnumber“Pass the previous result's nextOffset to get the next page.”
  • “Get one job posting by its jobId from search-jobs: the full description as text, locations, work arrangement, employment type, the pay range the posting states, Levels.fyi's estimated total compensat…”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • jobIdstringrequired“A jobId from search-jobs.”
  • send-feedback

    “Report wrong or missing Levels.fyi data, or a missing feature, to the Levels.fyi team.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    7 inputs, 2 required
    • kindstringrequired“What the report is about.”
    • messagestringrequired“What is wrong or missing, in the user’s words.”
    • toolNamestring“The tool whose result the report is about.”
    • companySlugstring“The company the report is about, as a slug.”
    • jobFamilySlugstring“The job family the report is about, as a slug.”
    • locationSlugstring“The location the report is about, as a slug.”
    • contactEmailstring“Only when the user wants a reply and gives this address.”
  • “Search across ALL entity types at once (companies, job families, job titles, focus tags, locations, and industries) by passing searchText (required) and get a single ranked list, each result tagged w…”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs, 1 required
    • searchTextstringrequired“Free-text query to search across all entity types (companies, job families, job titles, focus tags, locations, industries).”
    • limitnumber“Max results to return (1–15).”
    • excludeFamilyLikeTitlesboolean“When true, exclude TITLE results that are effectively the same as their job family.”
  • get-available-filters

    “List which inputs and filter values the free tier can use.”

    Publisher declares: read-only yes · destructive no · open-world no

    Takes no inputs.

  • get-metric-explanation

    “Explain a Levels.fyi compensation metric or concept (e.g.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • metricstringrequired“Compensation metric or concept to explain, e.g.”
  • get-domain-knowledge

    “Get reference knowledge about the Levels.fyi data model, by topic: compensation, levels, vesting, company_groups, locations, job_families, enums, negotiation_coaching.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input
    • topicstring“Data-model topic to fetch.”

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 2026-10-30.

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
95% of 104
Tools with a description
100% of 30
Typical description length
618 characters

The tool set

Counted from the listing

Tools
30
Size of the list
about 11,068 tokens for an agent to load (characters ÷ 4)
Naming
30 of 30 names use kebab-case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 30 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 2026-10-30 (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://mcp.levels.fyi/
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "levels-fyi": {
      "url": "https://mcp.levels.fyi/"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "levels-fyi": {
      "type": "http",
      "url": "https://mcp.levels.fyi/"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"levels-fyi","type":"http","url":"https://mcp.levels.fyi/"}'
Claude Code
claude mcp add --transport http levels-fyi https://mcp.levels.fyi/
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "levels-fyi": {
      "type": "streamableHttp",
      "url": "https://mcp.levels.fyi/",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "levels-fyi": {
      "httpUrl": "https://mcp.levels.fyi/"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.levels-fyi]
url = "https://mcp.levels.fyi/"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "levels-fyi": {
      "url": "https://mcp.levels.fyi/"
    }
  }
}
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://mcp.levels.fyi/ --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 #6

The 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 saysWe foundResultSource · date
Remote endpoint mcp.levels.fyi/Session openedmatchesour test · 2026-10-30
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-30
Repository github.com/Levels-fyi/levels-fyi-pluginOpens publiclymatchesapi.github.com · 2026-10-30

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace
fyi.levels
GitHub owner
an organization (Levels-fyi)
Repository
github.com/Levels-fyi/levels-fyi-plugin
Stars
0
Repository age
0–30 days
Last push
0–30 days ago
Archived
no

Source: the registry entry and api.github.com · 2026-10-30.

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 rating

4 of 4 record checks met · 4 do not apply · 1 not checked

  • 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 checkedRepository publishes a security policy (SECURITY.md)We did not read this repository's 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 2026-10-30. 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 fyi.levels/levels-fyi

Answered from the data above

Who publishes fyi.levels/levels-fyi?

The registry ties the namespace fyi.levels to the domain levels.fyi; only its owner can publish under it. Its linked repository is github.com/Levels-fyi/levels-fyi-plugin; GitHub reports its owner as Levels-fyi, an organization. These are facts from the registry and GitHub, not a rating.

Is fyi.levels/levels-fyi safe to install?

We do not rate servers as safe or unsafe. 4 of its 4 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 fyi.levels/levels-fyi need an API key or sign-in?

It opened a session without any credential on 2026-10-30. The registry entry declares no required credential; no declaration is not a guarantee.

Has fyi.levels/levels-fyi been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.

Where is the source code of fyi.levels/levels-fyi?

In github.com/Levels-fyi/levels-fyi-plugin, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A 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

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-30
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls 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-leak
    Plants 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
    ssrf
    Checks 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-confirmation
    Checks 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-handling
    Sends 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
    sampling
    Checks 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-data
    Checks 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-boundary
    Checks 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-channel
    Checks 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-hiding
    Checks 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
  • 16Sign-in redirect
    open-redirect
    Checks 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-deputy
    Checks 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
Does not apply to this server · 3
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks 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-validation
    Checks 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, 2026-10-30, 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.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,778 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 30 tools, 0 resources, 0 prompts.
  4. 5,768 msFinished: 3 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.

TopicAI-classified
pending: added in a later update
listed 2026-10-30; not classified yet
Pricing modelAI-classified
pending: added in a later update
the website is not read yet
Programming language
api.github.com · 2026-10-30
Hosting type
registry · 2026-10-30
MCP capability
tools
our test · 2026-10-30
Transport
streamable HTTP
registry · 2026-10-30
Required credentials
none declared
registry · 2026-10-30 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-10-30
Lifecycle status
registry · 2026-10-30
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
owner: an organization · repository age: 0–30 days · stars: 0–9
api.github.com · 2026-10-30
Maintenance
api.github.com · 2026-10-30
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-10-30

“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. “fyi.levels/levels-fyi: MCP server record.” Data checked 2026-10-30. https://protocolprobe.com/mcp/servers/fyi.levels/levels-fyi

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

ProtocolProbe: 4 of 4 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/fyi.levels/levels-fyi)](https://protocolprobe.com/mcp/servers/fyi.levels/levels-fyi)

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