workingproxysites.
[ new post ]
[ menu ]

directory

boards

[all]

information

MCP directory

Proxy Management MCP Servers: Account Tools & Access Scope

Compare MCP integrations with documented proxy-management capability, including publisher identity, credentials, tools and account restrictions.

Identify which MCP integrations expose documented proxy/account controls and what credentials those controls require.

  • Does the integration manage an account or only fetch a page through a proxy?
  • Which documented controls are read-only and which can change provider resources?
  • Who publishes the integration, and what account credentials does it receive?
4 documented listings

This collection covers our reviewed proxy and web-data catalog. It is not an exhaustive market survey or a performance ranking.

Category reviewed . Review due .

Compare documented requirements

4 of 4 listings
Clear filters

Swipe or scroll horizontally to compare requirements. Scroll back to the first column to see listing names.

MCP connections, tool scope and account requirements · alphabetical
MCP serverConnection & credentialsDocumented toolsBilling & restrictionsEvidence
Evomi MCPEvomi · official publisher

Inspect Evomi proxy products, targeting and usage, rotate sessions, and run scraping jobs through a local Python MCP server.

Details & setup →Provider discussionSourced JSON record
Local stdio · local

EVOMI_PUBLIC_API_KEY environment variable; a separate scraper key can optionally override automatic lookup.[1][2][3][4][6]

For this task: Read product, targeting and usage information, or change a session with rotate_proxy_session. Credential-returning tools have separate masking controls; check those before enabling the integration.[1][2]

  • list_proxy_products

    Inspect account products, gateways, ports and balances.[1]

  • list_proxy_targeting_options

    Find supported locations and network targeting values.[1]

  • get_proxy_usage

    Read recent bandwidth consumption.[2]

  • rotate_proxy_session

    Change the exit IP of a sticky session.[2]

  • scrape_url

    Retrieve a page with scraping options, including documented browser mode.[1]

  • search_domains

    Find domains from a search query.[2]

Scraping consumes credits according to mode and options. Proxy traffic uses the applicable product allowance. The software license does not include API usage.

Required product: Evomi Public API access plus the proxy or Scraper API product used by the tool.

Requirements & limitations
  • Credential tools can return live proxy passwords to the connected model and its client logs. EVOMI_HIDE_PROXY_PASSWORDS=1 masks or disables those outputs.
  • rotate_proxy_session changes a live session. Account and scraping tools are not all read-only.
  • The EVOMI_ENABLE_SPENDING flag controls browser-profile ordering; ordinary scraping still consumes credits when that flag is absent.
  • The uvx template adapts the documented evomi-mcp command using Astral’s tool launcher. Package 1.3.1 was reviewed; the unpinned command can install a newer release.
Documentation checkedReview due
6 source references
NodeMaven MCP (community)Artirain · community publisher

An unofficial local MCP server for inspecting NodeMaven proxy targeting, fetching pages through proxies and reading account location or usage information.

Details & setup →Provider discussionSourced JSON record
Local stdio · local

NODEMAVEN_API_KEY for account metadata; NODEMAVEN_PROXY_USERNAME and NODEMAVEN_PROXY_PASSWORD for proxy traffic.[1][2][3][7]

For this task: Community-maintained connection building, exit checks, location and usage reads. Building a proxy URL is local configuration; it is not an account change or rotation API.[4][1]

  • nodemaven_build_proxy_url

    Build a targeting URL locally, with the password masked unless explicitly revealed.[4]

  • nodemaven_check_proxy

    Send a proxy request to an IP information endpoint and return its reported exit details.[4][6]

  • nodemaven_fetch

    Retrieve a URL through the proxy and return bounded text or HTML.[4][6]

  • nodemaven_list_locations

    Read location choices through the account API.[4][8]

  • nodemaven_get_usage

    Read traffic, request or domain usage through the account API.[4][8]

The community code is MIT licensed. Proxy requests use a NodeMaven account’s paid traffic under its current subscription or pay-as-you-go terms.

Required product: NodeMaven proxy traffic

Requirements & limitations
  • Community project by Artirain; not affiliated with or maintained by NodeMaven.
  • Runs third-party Python code locally. The example pins the reviewed repository revision, but dependencies are resolved separately.
  • Account API calls need NODEMAVEN_API_KEY; proxy requests need a separate proxy username and password.
  • Page fetching performs HTTP retrieval and text conversion; it does not render JavaScript or control a browser.
  • Proxy checks contact an external IP information service; requests use the provider account’s traffic.
  • The URL builder masks the password by default; reveal_credentials can include it in tool output.
  • Source and documentation were reviewed; the package was not installed or connection-tested.
Documentation checkedReview due
9 source references
Novada MCPNovada · official publisher

Search, extract pages, use browser tools and configure proxy connections through Novada’s hosted endpoint or local npm package.

Details & setup →Provider discussionSourced JSON record
Streamable HTTP · hosted

Authorization: Bearer YOUR_NOVADA_API_KEY header.[3][5]

Local stdio · local

NOVADA_API_KEY environment variable.[3][5][6]

For this task: novada_proxy produces connection settings for an external HTTP client. Some additional account writes are local-only and require confirmation; use novada_discover to inspect the available surface.[2]

  • novada_setup

    Check API-key configuration and account readiness.[3]

  • novada_discover

    Inspect the tools available on this connection.[2]

  • novada_search

    Find pages using a search query and supported filters.[2]

  • novada_extract

    Retrieve content from selected URLs.[2]

  • novada_browser

    Perform documented page interactions.[2]

  • novada_proxy

    Produce proxy connection settings for an HTTP client.[2]

Scraping products draw from shared credits, with consumption depending on the product and request. Proxy plans and other product quotas can impose separate limits. Check both balance and the selected product.

Required product: Novada account with access to the scraping, browser or proxy product selected by the tool.

Requirements & limitations
  • Hosted and local connections expose different tools. Call novada_discover on the chosen connection instead of relying on a fixed tool count.
  • Persistent browser flows and some account-changing operations require the local server. Available operations must be checked on that profile.
  • Proxy connection output is used by your own HTTP client; it does not make arbitrary HTTP traffic flow through the MCP protocol.
  • The example uses an Authorization header for clients supporting remote headers. Query-string credential alternatives in the provider guide should not be shared.
Documentation checkedReview due
6 source references
Singapore Mobile Proxy MCPSingapore Mobile Proxy · official publisher

Fetch pages, check Singapore-localized Google results and inspect or rotate the provider’s mobile proxy exit through a hosted MCP endpoint.

Details & setup →Provider discussionSourced JSON record
Streamable HTTP · hosted

A Singapore Mobile Proxy MCP key in the x-api-key header.[1][2][5]

For this task: The documented tools inspect status and request exit-IP rotation for the Singapore service. They do not establish general country selection.[1]

  • my_proxy_status

    Read the current exit, carrier and remaining quota.[1]

  • fetch_url

    Fetch a URL as Markdown, text or HTML through the provider’s Singapore proxy.[1]

  • search_google

    Retrieve Singapore-localized Google organic results.[1]

  • rotate_ip

    Request a new Singapore mobile exit IP.[1]

MCP onboarding offers a limited trial; continued use requires the provider’s paid access. Confirm remaining quota and plan terms in the account.

Required product: Singapore Mobile Proxy MCP access and its proxy plan.

Requirements & limitations
  • This service specializes in Singapore; it is not a multi-country location selector.
  • The documented rotate_ip tool changes the proxy exit. Review that action before a workflow that relies on a stable session.
  • Carrier identity and connectivity were not independently tested.
  • The pricing page mixes bandwidth-labelled plans with unlimited wording. Confirm the applicable quota in the MCP account before relying on an allowance.
Documentation checkedReview due
5 source references

How to use this comparison

Compare the documented request interface, output and account product before checking price. A JSON response can contain raw HTML; it does not by itself establish structured extraction. A browser action in one request does not by itself establish a reusable browser session.

Each row keeps the publisher’s billing basis and restrictions alongside its sources. Unknown prices or limits remain unknown. These are documentation reviews; no live connection, purchase or comparative performance test is claimed.

Overdue records remain visible with a label. This collection leaves search indexing when its category review is overdue or fewer than 3 current, visible records qualify. Individual detail pages retain their own review policy.

The collection JSON link covers the whole category before filters. It returns summaries; use each listing’s Sourced JSON record link for full sources, connections, tools and billing.

Suggest a correction · Affiliate disclosure · Collection JSON summaries