Name: 2extract
Author: 2extract

2extract MCP

Web data access for AI agents: location targeting, usage limits, traffic and spend reports.

Tool-list grade A Remote · Streamable HTTP API key 20 tools v1.0.2 · 21 Oct 2026 MIT

No reviews yet by 2extractGitHub The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Web data access for AI agents: location targeting, usage limits, traffic and spend reports.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http 2extract-mcp https://mcp.2extract.com/mcp --header 'Authorization: Bearer ${API_KEY}'

# 2 — ask your agent for something these tools do
#   buildConnectionString, createProxyResource, deactivateProxyResource and 17 more

It needs API_KEY (2extract API key as a bearer token): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.

2extract costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher

2extract1 server

1 category

All 1 server

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.

Claude Codedeclared by this listing

This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads API_KEY (2extract API key as a bearer token) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx API_KEY … and open a new terminal (Windows).

claude mcp add --scope user --transport http 2extract-mcp https://mcp.2extract.com/mcp --header 'Authorization: Bearer ${API_KEY}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — 2extract API key as a bearer token. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.

What you approve

20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Build a ready-to-use username and connection string for a proxy resource. The tool retrieves the proxy credential and account prefix automatically, validates geo, network, and session parameters, and encodes them in the correct order. Response fields: docs://proxies/buildConnectionString.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID from listProxyResources.
country_code	string	no	Optional two-letter ISO country code, e.g. US.
state	string	no	Region extract_parameter. Requires country_code.
city	string	no	City extract_parameter. Requires country_code and state.
zip	string	no	ZIP value. Requires country_code; excludes state/city.
asn	integer	no	Residential ASN. Excludes location and isp.
isp	integer	no	Mobile ISP code. Excludes location and asn.
session	string	no	Optional alphanumeric sticky-session ID.
session_ttl_minutes	integer	no	TTL in minutes. Requires session.
strict	boolean	no	Strict sticky session. Requires session.

Create a new proxy resource. Response fields: docs://proxies/createProxyResource.

Parameter	Type	Required	Notes
name	string	yes	Proxy name: lowercase letters, digits, underscores only, max 50 characters. Immutable after creation.
proxy_type	string	yes	Proxy type, one of: residential, mobile
tariff_id	integer	yes	Tariff plan ID from listProxyPlans
countries	null/array	no	Country IDs; empty allows any country.
description	string	no	Free-text note, shown alongside this proxy in listProxyResources. Write enough detail to identify this proxy's purpose at a glance later — e.g. the project or task it's for, why it was created, its de
ip_whitelist	null/array	no	IP addresses allowed to authenticate with this proxy, e.g. ['203.0.113.1']. Empty or omitted means no IP restriction.
limits	null/object	no	Optional spend or traffic limit. Can also be set later via setProxyLimits.

Deactivate a proxy resource, stopping its traffic without deleting it. Use deleteProxyResource to permanently remove instead. Response fields: docs://proxies/updateProxyResource.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID. Get from listProxyResources.

Permanently delete a proxy resource. This action is irreversible — the proxy and all its settings will be removed. User confirmation is required before proceeding. Response fields: docs://proxies/deleteProxyResource.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID. Get from listProxyResources.
confirm	boolean	no	Set to true only after the user has explicitly confirmed the deletion. Skips the confirmation step.

Get the current account balance, overdraft limit, and proxy username prefix. Response fields: docs://account/getAccountBalance.

No parameter schema on file.

Get traffic usage statistics for the account over a date range. Response fields: docs://account/getAccountTrafficUsage.

Parameter	Type	Required	Notes
date_from	string	yes	Start date in YYYY-MM-DD format, e.g. 2024-01-01
date_to	string	yes	End date in YYYY-MM-DD format, e.g. 2024-01-31
user_proxy_list_id	string	no	Filter to a single proxy resource ID, from listProxyResources. Omit to get all proxies.
page	integer	no	Page number starting from 0, default 0
limit	integer	no	Items per page, default 100, max 200

Get full details of a specific proxy resource, including IP/host whitelists not present in listProxyResources. Response fields: docs://proxies/getProxyResource.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID, e.g. '86Rf07'. Get from listProxyResources.

Get balance transaction history for the account over a date range. Response fields: docs://account/listAccountBalanceHistory.

Parameter	Type	Required	Notes
date_from	string	yes	Start date in YYYY-MM-DD format, e.g. 2024-01-01
date_to	string	yes	End date in YYYY-MM-DD format, e.g. 2024-01-31
limit	integer	no	Items per page, default 100, max 200
page	integer	no	Page number starting from 0, default 0
order	string	no	Sort direction: asc or desc, default desc

List all available countries for proxy geo targeting, optionally filtered by name. Response fields: docs://geo/listGeoCountries.

Parameter	Type	Required	Notes
search	string	no	Optional country name filter, minimum 2 characters, e.g. 'United'

List tariff plans for a proxy type. Use the numeric id when calling createProxyResource. Response fields: docs://plans/listProxyPlans.

Parameter	Type	Required	Notes
proxy_type	string	yes	Proxy type to list plans for, one of: residential, mobile
enabled	null/boolean	no	Filter by enabled status. Default: true (only purchasable plans). Pass false to see all plans including disabled.
popular	null/boolean	no	Filter by popular flag. Omit to return all plans regardless of popularity.

List all proxy resources in the account, with tariff, limits, traffic, and spend detail. Response fields: docs://proxies/listProxyResources.

Parameter	Type	Required	Notes
search	string	no	Filter by proxy name (partial match, case-insensitive)
status	string	no	Filter by status: 'active', 'inactive', or comma-separated list e.g. 'active,inactive'
limit	integer	no	Items per page, default 100, max 200
page	integer	no	Page number starting from 0, default 0
order	string	no	Sort direction: asc or desc, default desc
order_by	string	no	Sort field: name, status, tariff.name, traffic_used.total_used, total_spent, created_at
statistic_from	string	no	Start date for per-proxy traffic statistics in YYYY-MM-DD format
statistic_to	string	no	End date for per-proxy traffic statistics in YYYY-MM-DD format

Generate a new password for a proxy resource. The old password is immediately invalidated — any running traffic using it will be interrupted. User confirmation is required before proceeding. Response fields: docs://proxies/regenerateProxyPassword.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID. Get from listProxyResources.
confirm	boolean	no	Set to true only after the user has explicitly confirmed the regeneration. Skips the confirmation step.

Search cities within a country and optional region (region_code from searchGeoRegions). Use search to narrow results — city lists can be large. Response fields: docs://geo/searchGeoCities.

Parameter	Type	Required	Notes
country_code	string	yes	ISO country code, e.g. 'US', 'DE'
region_code	integer	no	Numeric region code to filter cities, from searchGeoRegions' 'code' field, e.g. 77 for California
search	string	no	City name search, minimum 2 characters, e.g. 'Los'

Search the ISP catalog for mobile ISP targeting (mobile proxies only). Always resolve the code through this tool — never accept a real-world ASN number as a substitute. Response fields: docs://geo/searchGeoISP.

Parameter	Type	Required	Notes
search	string	no	ISP name substring search, minimum 3 characters, e.g. 'AT&T'
limit	integer	no	Max results, default 100, max 500

Search regions/states within a country. Response fields: docs://geo/searchGeoRegions.

Parameter	Type	Required	Notes
country_code	string	yes	ISO country code, e.g. 'US', 'DE', 'GB'
search	string	no	Optional region name filter, minimum 3 characters, e.g. 'California'

Search ZIP codes within a country, for use in proxy username params. Response fields: docs://geo/searchGeoZips.

Parameter	Type	Required	Notes
country_code	string	yes	ISO country code, e.g. 'US', 'DE'
search	string	no	ZIP substring search, minimum 3 characters, e.g. '123'
limit	integer	no	Max results, default 100, max 500

Replace the IP whitelist for a proxy resource, restricting authentication to the given IPs. Response fields: docs://proxy-settings/setProxyIpWhitelist.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID. Get from listProxyResources.
ips	null/array	yes	List of allowed IP addresses, e.g. ['203.0.113.1', '198.51.100.42']. Empty array removes all IP restrictions.

Set a traffic or spending limit on a proxy resource to control costs. Response fields: docs://proxy-settings/setProxyLimits.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID. Get from listProxyResources.
limit_type	string	yes	'money' = USD spend cap, 'traffic' = bytes cap
time_period	string	yes	Reset period for the limit counter, one of: daily, monthly
total_limit	number	yes	Limit value: USD amount for 'money' (e.g. 50.00), bytes for 'traffic' (e.g. 1073741824 = 1GB). Set to 0 to remove the limit.

Replace the target host whitelist for a proxy resource, restricting its traffic to the given domains. Response fields: docs://proxy-settings/setProxyTargetHosts.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID. Get from listProxyResources.
target_hosts	null/array	yes	List of allowed domains, e.g. ['example.com', '*.api.service.com']. Empty array removes all restrictions.

Update description, countries, status, IP whitelist, or limits in one call. Name and proxy_type are not mutable through this MCP tool. For single-field changes, prefer setProxyIpWhitelist, setProxyLimits, or deactivateProxyResource. Response fields: docs://proxies/updateProxyResource.

Parameter	Type	Required	Notes
id	string	yes	Proxy resource ID. Get from listProxyResources.
description	string	no	New description. See createProxyResource's description field for what to include.
countries	null/array	no	Replacement country IDs; empty clears.
status	string	no	New status, one of: active, inactive
ip_whitelist	null/array	no	New IP whitelist. Replaces the existing list entirely. Empty array removes all restrictions.
limits	null/object	no	New spend or traffic limit. Replaces the existing limit.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install 2extract or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.0.2 · scanned 23 Oct 2026

Graded from the tools this server lists, not from its source code.

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings0 threat · 1 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digest8acb4d07178f1e10593c22258dd3c6982bb4db9052d776b65aacb6596c77bb7b

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
buildConnectionString	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
createProxyResource	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
deactivateProxyResource	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
deleteProxyResource	external-sink	external-sink: declares destructiveHint: true, openWorldHint: true
getAccountBalance	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
getAccountTrafficUsage	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
getProxyResource	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
listAccountBalanceHistory	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
listGeoCountries	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
listProxyPlans	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
listProxyResources	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
regenerateProxyPassword	external-sink	external-sink: declares destructiveHint: true, openWorldHint: true
searchGeoCities	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
searchGeoISP	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
searchGeoRegions	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
searchGeoZips	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
setProxyIpWhitelist	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
setProxyLimits	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
setProxyTargetHosts	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
updateProxyResource	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digest8acb4d07178f1e10

Scanned2026-10-23

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.