Skip to content

MCP servers › com.getcloseknit › close-knit

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

com.getcloseknit/close-knit

London neighbourhoods and homes: crime, schools, prices, rents, commute, green space, sourced. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: data-and-databases · AI-classifiedversion 2.0.1streamable HTTP24 tools

Summary

com.getcloseknit/close-knit is a remote MCP server listed in the official MCP registry at version 2.0.1. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 24 tools, 1 resource and 1 prompt.

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  • not applicable: The version the registry lists can be installed and is not withdrawn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
Repository
link does not open publicly
Tools
24
Described as changing data
2 of 24 toolsAI-classified
Mainly works on
files and code on the machine it runs on; accounts and data in outside web servicesAI-classified
Topic
data-and-databasesAI-classified
Last tested
2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 1 tool whose name or declaration suggests it changes data (send_feedback). That is our reading of the names; we did not call it. Source: our connection, 2026-10-23.

Worth knowing before you connect it

  • 2 tools are described as changing something (build_watch_spec, send_feedback): 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.
  • The linked repository does not open publicly, so the code cannot be reviewed through it.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-23
Mode
read-only (no tool calls)
Latest version
2.0.1, published 2026-10-22 (registry, as of the 2026-10-23 snapshot)
First listed version
2026-10-22 (earliest version still in the registry; older removed versions would be earlier)
Version history
2 versions listed, all on 2026-10-22; 2 in the 90 days before the 2026-10-23 snapshot.
Most recent 2 versions
  • 2.0.1 · 2026-10-22
  • 2.0.0 · 2026-10-22
(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 2.0.1 (published 2026-10-22).

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
1resources
1prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on; accounts and data in outside web services.

2 of 24 tools are described as changing something (creating, editing, deleting, sending or running).

  • find_areason 4 other serversreads or searches

    “Shortlist London neighbourhoods for a household: budget, bedrooms, weighted priorities (crime, station access, price level, official deprivation decile, noise, disorder, energy rating, leasehold shar…”

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

    19 inputs, 1 required
    • marketstring“Buying or renting.”
    • max_budgetintegerrequired“Maximum price in £ (buy) or £ per month (rent).”
    • target_budgetinteger or null“Comfortable price; defaults to max less 8% (the site's own rule: £650k max → £600k).”
    • bedroomsinteger“Bedrooms needed (0 = studio).”
    • prioritiesarray“What matters, with importance 1-5 (criteria are ranked by importance, then in the order given; the order sets the weights).”
    • rangesarray“Any other map layer as a range with soft edges, e.g.”
    • budget_importanceinteger“Where the budget sits in the order (5 = first).”
    • budget_mustboolean“True = areas whose ballpark is over max_budget are out.”
    • near_stationsarray“Live within walking distance of these stations (e.g.”
    • boroughsarray“Live in these boroughs (uk:borough:E09…, from search_places).”
    • only_in_zonesboolean“With stations/boroughs given: True = only areas inside them (a must Where criterion); False = ranked first in the order, the fit falling with distance outside …”
    • zone_soft_metresinteger“Outside the zones the fit falls to 0 over this distance (when only_in_zones is False).”
    • exclude_area_idsarray“Areas the user already rejected — LSOA, MSOA or borough geography ids (boroughs and MSOAs expand to their LSOAs) — so they are not suggested again.”
    • include_over_budgetboolean“Keep areas whose typical home looks over budget.”
    • placesarray“Where the household goes — work, a gym, a particular school, friends (pinned: latitude/longitude from search_places) or the nearest of a kind (category).”
    • liked_area_idsarray“Areas the user liked: carried into the map link and highlighted there.”
    • property_typestring“House or flat, for the price comparison on the brief page (sales of similar homes).”
    • top_ninteger“How many areas to return.”
    • customarray“The user's own criteria from places on the map ('more cafés than kebab shops', 'near gyms'): a preset_id or a criterion, each scored by its percentile within t…”
  • open_shared_searchreads or searches

    “Open a search the user shared from the Close Knit site (a link with #profile=v1., v2.”

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

    2 inputs, 1 required
    • linkstringrequired“An Close Knit link the user shared (…#profile=v1.…, v2.”
    • top_ninteger“How many areas to return.”
  • find_similar_areason 1 other serverreads or searches

    “Neighbourhoods like one the user liked (crime, deprivation, income, price level and station access percentiles), optionally only cheaper ones: 'like this but cheaper / elsewhere'.”

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

    4 inputs, 1 required
    • area_idstringrequired“A neighbourhood (LSOA) the user liked.”
    • cheaperboolean“Only areas with a lower £/m² price level.”
    • bedroomsinteger or null“Adds a ballpark price for this size.”
    • top_ninteger“How many areas to return.”
  • get_area_overviewreads or searches

    “One neighbourhood in detail for a decision: local market (sales, turnover, leasehold share, £/m² medians, growth), the borough's official UK HPI (hpi: average price by type, 1/5/10-year change vs Lon…”

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

    2 inputs, 1 required
    • area_idstringrequired“Geography id, e.g.”
    • bedroomsinteger or null“Adds a ballpark price for this size.”
  • assess_listingreads or searches

    “Check one listing the user found against local evidence: asking price vs the neighbourhood's recorded £/m² (with floor area or a bedroom-based ballpark), turnover, growth, the borough's official HPI,…”

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

    11 inputs, 2 required
    • postcodestringrequired“Full postcode of the listing, e.g.”
    • asking_priceintegerrequired“£ (buy) or the rent in its rent_period (rent).”
    • marketstring“For sale or to rent.”
    • rent_periodstring“The rent's period: month = £ per calendar month, week = £ per week (converted ×52/12 for the comparison).”
    • bedroomsinteger or null“Bedrooms in the listing.”
    • floor_area_sqmnumber or null“Floor area in m² if the listing states it.”
    • floor_area_sqftnumber or null“Floor area in sq ft if the listing states it; converted server-side (1 sq ft = 0.092903 m²).”
    • property_typestring or null“Property type if the listing states it; used for a same-type comparison.”
    • tenurestring“Tenure if the listing states it; lease questions are hedged ('If leasehold') when unknown and skipped for freehold.”
    • share_percentnumber or null“Shared-ownership share for sale, e.g.”
    • listing_urlstring or null“Echoed back for citation only.”
  • list_metricson 19 other serversreads or searches

    “List every area metric the active release serves (id, unit, direction, available periods, legend, provenance, caveats), plus the My match factors (kind 'factor': disorder, epc-share, leasehold-share,…”

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

    1 input
    • compactboolean“Only id, unit, direction and defaultPeriod per metric: a small reply when you just need valid metric_id/period values.”
  • search_areason 3 other serversreads or searches

    “Resolve free text (area name, ONS code, postcode, street) to geography ids (uk:lsoa|msoa|borough:…) and, where recorded sales exist, address ids (uk:addr:…).”

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

    2 inputs, 1 required
    • qstringrequired“Free text: area name, ONS code (E01…), postcode, or street.”
    • limitinteger“Maximum results (1-25).”
  • get_area_metricreads or searches

    “Evidence-backed value of one metric for one area in one month: value, regional (londonPercentile: within the area's region, London for a London area; rankScope names it) and England percentiles, qual…”

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

    3 inputs, 2 required
    • area_idstringrequired“Geography id, e.g.”
    • metric_idstringrequired“Metric id from list_metrics, e.g.”
    • periodstring or null“Month, YYYY-MM.”
  • rank_areas_by_metricreads or searches

    “Rank every served area (or one region's, region='North West') by one metric for one month and return the top N with rank, value, unit and quality.”

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

    5 inputs, 2 required
    • metric_idstringrequired“Metric id from list_metrics.”
    • periodstringrequired“Month, YYYY-MM.”
    • top_ninteger“How many areas to return (1-50).”
    • orderstring“desc = highest value first.”
    • regionstring or null“Only areas of one English region: its code (E12000001-E12000009) or name, e.g.”
  • get_address_historyon 1 other serverreads or searches

    “Recorded achieved sale prices for one address id (HM Land Registry Price Paid, GBP, with the EPC floor area where matched; no per-sale GBP/m2).”

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

    1 input, 1 required
    • address_idstringrequired“Address id returned by search_areas (uk:addr:…).”
  • get_home_priceson 1 other serverreads or searches

    “One London home's recorded sales (date, price, HM Land Registry link) and prices in its area today: the middle half (25th-75th percentile) of same-type standard sales since three years back, each adj…”

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

    1 input, 1 required
    • property_refstringrequired“UPRN (digits), an address id (uk:addr:…) as returned by search_places, or an address fragment, e.g.”
  • match_areasreads or searches

    “Score every area against a household's ordered criteria (preference-profile.v2: budget, ranges on any map layer, places, where zones, own criteria; must = filter).”

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

    2 inputs, 1 required
    • profileobjectrequired“preference-profile.v2 (preferred): {schemaVersion: 'preference-profile.v2', market buy|rent, targetBudget, maximumBudget, bedrooms, criteria: [...]} where crit…”
    • top_ninteger“How many of the best-scored areas to list (1-100).”
Show 12 more tools
  • get_market_depthon 1 other serverreads or searches

    “Local market depth of one LSOA or MSOA from HM Land Registry Price Paid (standard category A sales only): sales in the last 12 months, turnover (% of EPC-linked homes that sold), the leasehold share …”

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

    1 input, 1 required
    • area_idstringrequired“LSOA or MSOA geography id, e.g.”
  • get_nearby_sales_summaryreads or searches

    “Counts and median GBP/m2 of other homes' recorded sales in the same building (postcode, house number or name, street) and on the same street (other buildings) as one address id, last 10 years.”

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

    1 input, 1 required
    • address_idstringrequired“Address id returned by search_areas (uk:addr:…).”
  • get_area_evidence_packreads or searches

    “One cited evidence pack for an area: market depth (as get_market_depth), the latest recorded crime rate, road and rail noise shares, state schools within 1.5 km with their standing Ofsted grade, and,…”

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

    2 inputs, 1 required
    • area_idstringrequired“Geography id, e.g.”
    • address_idstring or null“Optional address id (uk:addr:…) inside the area: adds its building and street sale aggregates.”
  • search_placeson 72 other serversreads or searches

    “Resolve a place the user mentions (station, borough, neighbourhood, postcode, street) to ids.”

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

    2 inputs, 1 required
    • qstringrequired“A station, borough, neighbourhood, postcode or street.”
    • limitinteger“Results per kind.”
  • get_commutereads or searches

    “Door-to-door minutes from one neighbourhood to the user's places on a weekday morning, by public transport (R5 on TfL timetables), bike (at the speed Santander Cycles riders reach; checked against Tf…”

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

    2 inputs, 2 required
    • area_idstringrequired“The neighbourhood (LSOA) to travel from.”
    • placesarrayrequired“Pinned places (latitude/longitude) to reach.”
  • get_flood_riskon 1 other serverreads or searches

    “Flood bands for an area's land (rivers/sea, surface water) and, with a UPRN, that home's own bands.”

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

    2 inputs, 1 required
    • area_idstringrequired“Geography id, e.g.”
    • uprnstring or null“A home's UPRN for its own bands; without it, only the area's land bands.”
  • get_rent_levelsreads or searches

    “Median monthly rent by bedroom count for areas (the figure the site shows).”

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

    2 inputs, 2 required
    • area_idsarrayrequired“Geography ids, e.g.”
    • bedroomsintegerrequired“Bedroom count; the site shows rents per bedroom count.”
  • get_listing_search_linksreads or searches

    “Pre-filtered searches on Rightmove, Zoopla, OnTheMarket (and OpenRent for rentals) for the postcode districts of shortlisted areas.”

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

    5 inputs, 2 required
    • area_idsarrayrequired“LSOA ids from find_areas.”
    • marketstring“Buying or renting.”
    • max_priceintegerrequired“£ (buy) or £ per month (rent).”
    • min_bedroomsinteger“Minimum bedrooms.”
    • outcodes_per_areainteger“Postcode districts per area (busiest first).”
  • list_custom_presetsreads or searches

    “Ready-made custom criteria built from places on OpenStreetMap, with neutral descriptive names: kebab shops vs cafés, specialty coffee vs kebab shops, sandwich chains vs bakery chains, independent vs …”

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

    Takes no inputs.

  • evaluate_custom_criterionreads or searches

    “Evaluate a criterion from places on the map for every London neighbourhood ('where are more cafés than kebab shops', 'most gyms in the area'), counting the places inside each neighbourhood's boundary…”

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

    5 inputs
    • preset_idstring or null“A ready-made criterion from list_custom_presets.”
    • criterionnull“Or the user's own criterion.”
    • directionstring or null“Which end the user wants (for the top list and the map link).”
    • area_idsarray“Also report these areas (LSOA ids from search_places).”
    • top_ninteger“How many top and bottom areas to list.”
  • build_watch_speccreates or changes datadescribed as changing data

    “Turn a finished search into a watch: portal searches per postcode district, filters, a state file path for de-duplication and a ready prompt for a scheduled task in the user's Claude that reports onl…”

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

    7 inputs, 3 required
    • namestringrequired“Short name, e.g.”
    • area_idsarrayrequired“LSOA ids to watch.”
    • marketstring
    • max_priceintegerrequired“£ (buy) or £ per month (rent).”
    • min_bedroomsinteger
    • must_havesstring“Free-text requirements the agent checks per listing.”
    • frequencystring
  • send_feedbackon 46 other serverssends messagesdescribed as changing data

    “Send feedback about Close Knit to the team: a bug, missing or wrong data, an idea, or what worked.”

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

    5 inputs, 2 required
    • kindstringrequired“bug = a tool failed or misbehaved; missing-data / wrong-data = an answer lacked or got a fact wrong; idea = something to add; praise = what worked well.”
    • messagestringrequired“What happened or what would help, in a few sentences: the product, never the person.”
    • ratinginteger or null“How useful Close Knit was, 1-5, if the user said.”
    • toolsarray“The Close Knit tools it is about, e.g.”
    • clientstring or null“The AI client, e.g.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “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 24 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
97% of 87
Tools with a description
100% of 24
Typical description length
491 characters

The tool set

Counted from the listing

Tools
24
Size of the list
about 15,026 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://getcloseknit.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "close-knit": {
      "url": "https://getcloseknit.com/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "close-knit": {
      "type": "http",
      "url": "https://getcloseknit.com/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"close-knit","type":"http","url":"https://getcloseknit.com/mcp"}'
Claude Code
claude mcp add --transport http close-knit https://getcloseknit.com/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://getcloseknit.com/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 getcloseknit.com/mcpSession openedmatchesour test · 2026-10-23
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-23
Repository github.com/bmsdave/close-knit-mcpDoes not open (not found or private)differsapi.github.com · 2026-10-22

Who made it?

Feature #7 · lineage

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

Namespace
com.getcloseknit
Repository
github.com/bmsdave/close-knit-mcp — does not open publicly

Source: the registry entry and api.github.com · 2026-10-22.

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

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 linked repository returned HTTP 404: it does not exist or is private.
  • 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 com.getcloseknit/close-knit

Answered from the data above

Is com.getcloseknit/close-knit 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: The repository it links to does not open publicly, so its code cannot be inspected through that link. 2 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.

Does com.getcloseknit/close-knit 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 com.getcloseknit/close-knit been security tested?

Partly. 4 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. No security verdict is published before verification.

What can com.getcloseknit/close-knit 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 and send messages. We did not call any tool, so this describes the text, not the behaviour.

Can com.getcloseknit/close-knit change or delete data?

2 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.

Where is the source code of com.getcloseknit/close-knit?

The registry links to github.com/bmsdave/close-knit-mcp, but that link does not open publicly, so the code cannot be inspected through it.

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: exercised
  13. Fake assistant turns: exercised
  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

4 exercised11 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). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 4
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.exercised
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.exercised
Not run, with the reason · 11
  • 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
  • 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
  • 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. 1,109 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 24 tools, 1 resource, 1 prompt.
  4. 4,558 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.

TopicAI-classified
AI-classified · 2026-10-23
Pricing modelAI-classified
no value
The website listed in the registry is a code-hosting, package or marketplace page, not the product's own site.
Programming language
does not apply
no existing GitHub repository
Hosting type
registry · 2026-10-23
MCP capability
prompts, resources, 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
not stated
repository link is dead (HTTP 404), so activity cannot be read
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. “com.getcloseknit/close-knit: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/com.getcloseknit/close-knit

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/com.getcloseknit/close-knit)](https://protocolprobe.com/mcp/servers/com.getcloseknit/close-knit)

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