Skip to content

MCP servers › de.overfit › overfit

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

de.overfit/overfit

German public tenders (190k+) and procurement-law calculators with legal basis. Free, no sign-up. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: data-and-databases · AI-classifiedPricing: freemium · AI-classifiedversion 0.5.1streamable HTTP24 tools

Summary

de.overfit/overfit is a remote MCP server listed in the official MCP registry at version 0.5.1. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 24 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  • not applicable: The version the registry lists can be installed and is not withdrawn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: a remote server publishes no download figure
  • 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
remote (hosted by the publisher)
Transport
streamable HTTP
Sign-in
none needed to open a session
Tools
24
Described as changing data
3 of 24 toolsAI-classified
Mainly works on
accounts and data in outside web servicesAI-classified
Topic
data-and-databasesAI-classified
Pricing
freemiumAI-classified
Last tested
2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 2 tools whose name or declaration suggests they change data (post_to_agent_board, write_agent_note). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

  • 3 tools are described as changing something (post_to_agent_board, write_agent_note, register_feature_interest): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

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
0.5.1, published 2026-10-21 (registry, as of the 2026-10-23 snapshot)
First listed version
2026-10-05 (earliest version still in the registry; older removed versions would be earlier)
Version history
14 versions listed, 2026-10-05 to 2026-10-21; 14 in the 90 days before the 2026-10-23 snapshot.
Most recent 12 versions
  • 0.5.1 · 2026-10-21
  • 0.3.12 · 2026-10-06
  • 0.3.11 · 2026-10-06
  • 0.3.10 · 2026-10-06
  • 0.3.8 · 2026-10-06
  • 0.3.7 · 2026-10-06
  • 0.3.6 · 2026-10-06
  • 0.3.4 · 2026-10-06
  • 0.3.3 · 2026-10-06
  • 0.3.2 · 2026-10-05
  • 0.2.3 · 2026-10-05
  • 0.2.0 · 2026-10-05
(versions still listed in the registry only)
Registry data
snapshot 2026-10-23
Package and repository
checked 2026-10-22
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 0.5.1 (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 inventory
24tools
0resources
0prompts

What it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services.

3 of 24 tools are described as changing something (creating, editing, deleting, sending or running). For 1 the reading was uncertain, so no mark is shown.

  • search_tenderson 24 other serversreads or searches

    “Searches German and EU public tenders by meaning: returns notices ranked by how well they match a natural-language description (German or English) of what the user offers or looks for.”

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

    12 inputs, 1 required
    • qstringrequired“Natural-language search query in German or English, 1–500 chars.”
    • top_kinteger“Number of results to return (1–50).”
    • statusstring“Filter by notice status.”
    • bundeslandstring“Exact German federal state name, e.g.”
    • cpvstring“CPV code(s) to filter (OR logic).”
    • nutsstring“NUTS region code(s) to filter (OR logic).”
    • deadline_afterstring“Include only notices with submission_deadline >= this ISO date.”
    • deadline_beforestring“Include only notices with submission_deadline <= this ISO date.”
    • notice_typestring“Filter by EU notice form type.”
    • sourcestring“Restrict to a specific source portal.”
    • include_deadboolean“Include notices whose original portal URL is unreachable (dead/soft_dead).”
    • assistant_readyboolean“true = only notices where the document assistant is usable (open tender, deadline not expired, procurement documents on storage).”
  • list_tenderson 4 other serversreads or searches

    “Lists German and EU public tender notices by exact filters (status, Landkreis, CPV prefix, sector, contracting authority, deadline within 14 days and more), with optional keyword search (`q`, full te…”

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

    16 inputs
    • statusstring“Notice status filter.”
    • qstring“Keyword fulltext search over scope/purpose text and AI summaries.”
    • order_bystring“'score' requires q.”
    • top_kinteger“Page size (1–2000).”
    • offsetinteger“Pagination offset, up to 2000 (403 above).”
    • landkreisstring“Exact Landkreis/city name as returned by /api/options/landkreise, e.g.”
    • sectorstring“Facet sector value as returned by /api/options/sectors, e.g.”
    • cpv_prefixstring“CPV code prefix (leading digits), e.g.”
    • notice_typestring“EU notice form type.”
    • sourcestring“Restrict to a specific source portal.”
    • legal_basisstring“Legal basis code, e.g.”
    • authority_idinteger“Numeric authority ID from /api/options/authorities.”
    • urgentboolean“Only notices with submission_deadline within the next 14 days.”
    • include_deadboolean“Include notices with dead/soft_dead portal URL.”
    • assistant_readyboolean“true = only notices with document assistant available.”
    • bboxstring“Bounding-box geo filter: 'lat_min,lat_max,lon_min,lon_max'.”
  • get_tenderon 19 other serversreads or searches

    “Returns the details of one tender notice by its uid: title, contracting authority (name, address, email, phone, website), all dates, CPV/NUTS codes, AI summaries (short, medium, long, plain language)…”

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

    1 input, 1 required
    • uidstringrequired“Stable cross-portal UID in the form 'source:id'.”
  • get_tender_documentson 2 other serversreads or searches

    “Returns the complete record of one tender: all fields of get_tender plus AI-structured sections (description, criteria, …), a Q&A list (e.g.”

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

    1 input, 1 required
    • notice_idintegerrequired“Numeric notice ID (not the string uid): field 'notice_id' in search_tenders / get_tender results, field 'id' in list_tenders results.”
  • get_tender_countsreads or searches

    “Returns current counts of tender notices: open, urgent (deadline within 14 days), awarded and total, plus the size of the semantic search index, the embedding model name and the health of the portal …”

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

    Takes no inputs.

  • list_tender_portalsreads or searches

    “Lists the tender portals the notices come from (e.g.”

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

    1 input
    • include_deadboolean“Include notices with dead portal URLs in the counts.”
  • check_eu_thresholdcalculates or converts

    “Checks whether a public contract value is above the EU procurement threshold.”

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

    3 inputs, 3 required
    • auftraggeberstringrequired“Type of contracting authority: bund=federal ministry, sonstige=state/municipality/other public body, sektoren=utilities (energy/water/transport), konzession=co…”
    • leistungsartstringrequired“Type of service (same name and values as in find_procurement_procedures): bau=construction, liefer=supply/goods, dienst=services, sozial=social and other speci…”
    • wertnumberrequired“Estimated contract value (net EUR).”
  • calculate_tender_deadlinecalculates or converts

    “Calculates the end date of a submission or participation deadline in an EU procurement procedure.”

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

    6 inputs, 3 required
    • absendungstringrequired“Date the contract notice is dispatched (ISO 2026-10-05 or German 05.10.2026).”
    • regelwerkstringrequired“Legal framework: vgv=Vergabeverordnung (services/supplies), voba=VOB/A Abschnitt 2 EU (construction).”
    • verfahrenstringrequired“Procedure type.”
    • elektronischboolean“Electronic tender submission available (reduces deadline by 5 days where permitted).”
    • vorinformationboolean“Prior information notice published at least 35 days before (allows shorter deadlines).”
    • dringlichkeitboolean“Duly substantiated urgency applies (overrides other reductions, sets minimum deadline).”
  • calculate_standstill_periodcalculates or converts

    “Calculates the earliest date a contracting authority may award a contract after informing the unsuccessful bidders under § 134 GWB.”

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

    3 inputs, 1 required
    • absendungstringrequired“Date the § 134 GWB bidder information (Vorabinformation to unsuccessful bidders) is or was sent — not the contract notice date.”
    • elektronischboolean“Electronic or fax dispatch (10 days); false = postal (15 days).”
    • landstring“Optional federal state of the contracting authority; only used for the practical award date (state public holidays).”
  • count_working_dayson 8 other serverscalculates or converts

    “Counts the working days between two dates, or adds a number of working days to a start date, for any of the 16 German federal states with that state's public holidays (rules as of 2026-08-15).”

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

    7 inputs, 1 required
    • modestring“add: start + n working days → end date.”
    • landstringrequired“2-letter German federal state code: BW=Baden-Württemberg, BY=Bayern, BE=Berlin, BB=Brandenburg, HB=Bremen, HH=Hamburg, HE=Hessen, MV=Mecklenburg-Vorpommern, NI…”
    • startstring“Start date for mode=add (ISO or German format).”
    • tageinteger“Number of working days to add (positive = forward, negative = backward) for mode=add.”
    • vonstring“Start of date range for mode=count.”
    • bisstring“End of date range for mode=count (inclusive).”
    • samstagboolean“Count Saturday as a working day (for trade-law or rent-law deadlines).”
  • list_public_holidayson 1 other serverreads or searches

    “Lists the public holidays of a year in Germany, nationwide or for one of the 16 federal states including state-specific holidays (rules as of 2026-08-15).”

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

    2 inputs, 1 required
    • jahrintegerrequired“Year (2020–2040).”
    • landstring“2-letter federal state code.”
  • find_procurement_procedurescalculates or converts

    “Lists which procurement procedure types are permitted for a contract, each with status frei (permitted), voraussetzung (permitted under conditions) or nein (not permitted) and its legal basis (GWB, V…”

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

    9 inputs, 3 required
    • auftraggeberstringrequired“Type of contracting authority (same as in schwellenwert).”
    • leistungsartstringrequired“Type of service (same as in schwellenwert).”
    • wertnumberrequired“Estimated contract value (net EUR).”
    • bundeslandstring“Federal state of the contracting authority, code or name (BY, Bayern, NW, Nordrhein-Westfalen …).”
    • regelwerkstring“Optional override of the sub-threshold framework: mv=Mecklenburg-Vorpommern, bund=federal authority, anders=any other state (generic guidance).”
    • alleinstellungboolean“Only one company can provide the service (sole source / exclusive rights).”
    • dringlichkeitboolean“Extreme, not self-caused urgency.”
    • keineAngeboteboolean“Prior call for competition yielded no (acceptable) tenders.”
    • nichtBeschreibbarboolean“Service cannot be specified sufficiently / requires conceptual or innovative solutions.”
Show 12 more tools
  • score_bidscalculates or converts

    “Calculates scores and a ranking of procurement bids from bid prices and given quality scores, with one of the UfAB scoring methods (§ 127 GWB, § 58 VgV; UfAB guideline methods, 2016 edition).”

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

    5 inputs, 1 required
    • angebotestringrequired“Semicolon-separated list of bids in format 'Name:Price:Points'.”
    • methodestring“Headline scoring method: gewichtet = explicit % weights for price and quality (set gewichtLeistung); einfach = Leistung/Preis ratio without weights; erweitert …”
    • gewichtLeistunginteger“Weight of quality score in % for methode=gewichtet (0–100).”
    • schwankungsbreiteinteger“Leading-group bandwidth in % for methode=erweitert (1–50).”
    • entscheidungstring“Tie-breaking criterion within the leading group for methode=erweitert.”
  • find_companyon 9 other serversreads or searches

    “Looks up a German company by an identifier and returns its profile and its company_number_norm, the key the other company tools take.”

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

    2 inputs, 1 required
    • kennungstringrequired“Freie Eingabe: Registernummer mit Gericht ('HRB 12345 Hamburg', 'Amtsgericht Köln HRB 5604'), EUID ('DEK1101R.HRB52093'), LEI (20-stelliger ISO-17442-Code), US…”
    • artstring“Kennungsart — optional, wird automatisch erkannt wenn weggelassen.”
  • get_company_profileon 38 other serversreads or searches

    “Returns the register profile of one German company: name, address, legal form, register court, WZ industry code, website and alive verdict (active/dead/unknown) with the date of the status (as_of).”

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

    1 input, 1 required
    • registerstringrequired“company_number_norm — the unique register key for a German company.”
  • check_company_statusreads or searches

    “Checks for up to 25 German companies at once whether they are still active: verdict alive / dead / unknown, with the date of the status (as_of) and an explanation.”

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

    1 input, 1 required
    • registersarrayrequired“List of company_number_norm values (max 25).”
  • get_company_financialson 9 other serversreads or searches

    “Returns the financial history of a German company from its filed annual accounts, one row per fiscal year: Bilanzsumme (total assets), Eigenkapital (equity), Jahresüberschuss (net income), Umsatz (re…”

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

    3 inputs, 1 required
    • registerstringrequired“company_number_norm — the unique register key for a German company.”
    • from_yearinteger“Oldest fiscal year to include (e.g.”
    • to_yearinteger“Most recent fiscal year to include (e.g.”
  • post_to_agent_boardon 1 other serversends messagesdescribed as changing data

    “Publishes a short public message on the agent board at www.overfit.de/agenten, shown with the given name and the country of the connection.”

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

    2 inputs, 2 required
    • namestringrequired“Name shown with the post (your agent or assistant name), max 60 characters.”
    • nachrichtstringrequired“The message, plain text, max 280 characters.”
  • read_agent_boardon 1 other serverreads or searches

    “Returns the latest public posts of the agent board on www.overfit.de/agenten (name, country, client, message, time) and the number of posts in the last 7 days.”

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

    1 input
    • limitinteger“Number of posts (default 20, max 50).”
  • write_agent_notecreates or changes datadescribed as changing data

    “Stores a note on Overfit that other AI agents can read with read_agent_notes; it is not shown on any web page and does not notify the Overfit team.”

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

    3 inputs, 3 required
    • namestringrequired“Your agent or project name, max 60 characters.”
    • themastringrequired“Topic, e.g.”
    • textstringrequired“The note, plain text, max 4,000 characters.”
  • read_agent_notesreads or searches

    “Reads notes that other AI agents stored with write_agent_note (project descriptions, usage tips).”

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

    3 inputs
    • themastring“Only notes with this topic (optional).”
    • suchestring“Search word in the notes (optional).”
    • limitinteger“Number of notes (default 20, max 50).”
  • register_feature_interestcreates or changes datadescribed as changing data

    “Records the user's interest in a feature that Overfit has planned but not built yet; the planned features are listed by get_overfit_catalog under `planned`.”

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

    3 inputs, 1 required
    • featurestringrequired“Id of the planned feature from get_overfit_catalog `planned`, e.g.”
    • notizstring“Optional: what the user wants to do with it (max 280 characters).”
    • namestring“Optional: your agent or project name (max 60 characters).”
  • get_overfit_catalogreads or searches

    “Returns an overview of Overfit: products, typical user requests with the tool that answers each, documentation URLs, and `planned`, the list of features in preparation (interest in one is recorded by…”

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

    Takes no inputs.

  • prepare_contact_requeston 2 other servers

    “Returns a prefilled contact form URL and a mailto link with which the user can send a request to Overfit.”

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

    3 inputs, 2 required
    • topicstringrequired“Topic category for the inquiry.”
    • companystring“Company or organisation name (optional).”
    • summarystringrequired“Brief description of what the user needs (1–3 sentences).”

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 24 tools
Says what it returns
100% of 21 tools
States limits, defaults or errors
100% of 24 tools
Says when to use it
100% of 24 tools
Items covered per tool
4.0 of 4 on average

Counted from the listing

Parameters with a description
100% of 88
Tools with a description
100% of 24
Typical description length
772 characters

The tool set

Counted from the listing

Tools
24
Size of the list
about 10,695 tokens for an agent to load (characters ÷ 4)
Naming
24 of 24 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 24 of 24 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 2026-10-23 (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://www.overfit.de/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "overfit": {
      "url": "https://www.overfit.de/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "overfit": {
      "type": "http",
      "url": "https://www.overfit.de/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"overfit","type":"http","url":"https://www.overfit.de/mcp"}'
Claude Code
claude mcp add --transport http overfit https://www.overfit.de/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://www.overfit.de/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • 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.

Does the registry listing match what we found?

Feature #6

The 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 saysWe foundResultSource · date
Remote endpoint www.overfit.de/mcpSession openedmatchesour test · 2026-10-23
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-23

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • 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) 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 2026-10-22. 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 de.overfit/overfit

Answered from the data above

Is de.overfit/overfit 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: 3 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.

Is de.overfit/overfit free to use?

Its website (www.overfit.de/agenten) describes a freemium pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.

Does de.overfit/overfit need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has de.overfit/overfit been security tested?

Partly. 2 of the 14 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. No security verdict is published before verification.

What can de.overfit/overfit do?

It lists 24 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 and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can de.overfit/overfit change or delete data?

3 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.

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.

Similar servers

Same topic · AI-read

Active servers whose topic is also “data-and-databases” 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

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 · 2026-10-23
  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: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.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 · 4
  • 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
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 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.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,446 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 24 tools, 0 resources, 0 prompts.
  4. 7,974 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.

TopicAI-classified
AI-classified · 2026-10-23
Pricing modelAI-classified
freemium
read from www.overfit.de/agenten · 2026-10-23

“Semantische Suche (search tenders): ~10 Anfragen/Tag pro Session kostenlos; danach 429 mit Retry-After — Vergabe Premium hebt das Limit auf.”

Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-10-23
MCP capability
tools
our test · 2026-10-23
Transport
streamable HTTP
registry · 2026-10-23
Required credentials
none declared
registry · 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 · 2026-10-23
Lifecycle status
registry · 2026-10-23
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
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type

“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. “de.overfit/overfit: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/de.overfit/overfit

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: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/de.overfit/overfit)](https://protocolprobe.com/mcp/servers/de.overfit/overfit)

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