Reference

Integrations

Argus speaks the Model Context Protocol, so an agent that already knows how to use tools can drive your profiles without being taught an API. Connecting installs nothing.

On this page

Agents over MCP

MCP is how a coding agent discovers what a program can do. The agent asks for a tool list, gets one back with names, descriptions and argument schemas, and calls what it needs — no wrapper, no SDK, nothing to keep in step with a changelog.

The Argus server runs from inside the launcher's own application bundle, started with ELECTRON_RUN_AS_NODE. There is no package to install and nothing new listening: it speaks JSON-RPC over stdin and stdout to the client that launched it, and reaches the local API on your behalf.

For most clients the launcher writes the config file for you and shows you the path first. Two of them have no file it can write, and say so by handing over a snippet instead.

This is a local API. It listens on loopback on the machine running Argus, and nothing off that machine can reach it. There is no hosted web API.

The API and the MCP tools are on every plan, including Free. A plan sets how many profiles, seats and automations a workspace gets — it does not decide whether the API answers. What the server is, what an agent can reach through it and where its reach ends is on the MCP page; what follows here is the wiring.

Supported clients

Coding agents

Claude Code

Anthropic's coding agent CLI. Drive profiles as tools from any project.

Config: ~/.claude.json
Key: mcpServers.argus

Run /mcp in any project — argus should be in the list.

Codex

OpenAI's coding agent CLI. Same tools, wired into Codex's own config.

Config: ~/.codex/config.toml
Key: [mcp_servers.argus]

Codex reads its MCP servers at startup — ask it what tools it has and the argus ones should be there.

Cursor

The AI editor. Registered in Cursor's global MCP config.

Config: ~/.cursor/mcp.json
Key: mcpServers.argus

Open Cursor Settings → MCP: argus should be listed and switched on.

Gemini CLI

Google's coding agent CLI. Same tools, in its own settings file.

Config: ~/.gemini/settings.json
Key: mcpServers.argus

Run /mcp — argus should be in the list.

Windsurf

The Codeium editor. Registered for Cascade to use.

Config: ~/.codeium/windsurf/mcp_config.json
Key: mcpServers.argus

Open Cascade's plugin panel: argus should be listed there.

VS Code

Agent mode in Visual Studio Code, through its user MCP config.

Config: Code/User/mcp.json
Key: servers.argus

Switch Chat to Agent mode and open the tools picker — the argus tools should be listed.

Zed

Zed's agent panel, through its context server settings.

Config: ~/.config/zed/settings.json
Key: context_servers.argus

Check the agent panel's settings: argus should appear under context servers.

Automation

OpenClaw

Personal assistant gateway across chat channels.

Config: ~/.openclaw/openclaw.json
Key: mcp.servers.argus

It loads its config at startup — argus should show up among its tools.

Set up by hand

These two have no config file Argus can write. Connecting them means handing over a snippet rather than pretending to wire them up.

Hive

by hand

Multi-agent runtime. Run QA and monitoring sweeps across many profiles at once.

Config: its own .env
Key: environment variables

Hive reads the .env at startup — its first sweep will use this key.

Any other MCP client

by hand

Anything that speaks MCP. Copy the server block into its config yourself.

Config: whatever your client reads
Key: mcpServers.argus

Your client should list argus among its MCP servers once it is back up.

Setting it up by hand

For everything above except Hive and “Any other MCP client”, Argus writes this block for you and shows you the file path before it touches anything. If you would rather do it yourself, or your client is not on the list, this is the shape.

mcp.json

{
  "mcpServers": {
    "argus": {
      "type": "stdio",
      "command": "Argus Launcher",
      "args": ["<the path shown after you connect>"],
      "env": {
        "ELECTRON_RUN_AS_NODE": "1",
        "ARGYS_API_TOKEN": "<your key>",
        "ARGYS_API_BASE": "http://127.0.0.1:39219"
      }
    }
  }
}

Hive reads environment variables out of its own .env instead:

.env

ARGYS_API_BASE=http://127.0.0.1:39219
ARGYS_API_TOKEN=<your key>

Restart the client afterwards. Every one of these reads its MCP config at process start and there is no reload signal Argus can send.

What an agent gets

143 tools, and the instructions the server hands the model on connect:

Drive Argus anti-detect browser profiles. Each profile is an isolated browser identity with its own proxy, fingerprint and cookie jar. Typical flow: argus_list_profiles, then argus_launch_profile, then argus_navigate / argus_read_page / argus_screenshot, then argus_close_profile. A launched session carries whatever identity the profile already holds, including its cookies — do not send it anything the profile is not meant to have. The launch reply carries a `warnings` array: a non-empty one means that profile shares its cookie-set or its proxy past the limit, so tell the user rather than opening a batch silently, and call argus_sharing_report before a batch to see the whole picture in one call. This workspace may also hold PROJECTS: named pieces of work that span profiles, proxies and automations, each with a goal, a set of rules and the notes and runbooks the in-app assistant keeps about it. Call argus_list_projects to see them and argus_project_context for one project's brief and rules — read those BEFORE acting on anything the project holds, because they are where its constraints are written down. Every other document is exposed as a resource (argus://project/<id>/<path>), so list them and read only the ones you need. argus_delegate hands a goal to Argus's own orchestrator, which already has that project's context loaded.

127 tools wrap an endpoint

argus_list_profiles

List profiles (optional ?folder=<id>)

argus_get_profile

Read one profile

argus_create_profile

Create a profile

argus_update_profile

Update name, status, tags, colour, avatar, folder, proxy mode, start URL or launch automation

argus_profile_notes

Read a profile's notes, newest first

argus_add_profile_note

Append a note to a profile

argus_assign_proxy

Put a profile on a proxy from the library

argus_sharing_report

Every cookie-set and proxy shared past its limit, with the limits themselves

argus_launch_profile

Open a profile for automation; returns its CDP url. Reuses a running session unless relaunch is set

argus_profile_session

Where a running profile's CDP endpoint is, without launching it

argus_close_profile

Close a session this key opened

argus_delete_profile

Move a profile to Trash (permanent: true to purge; the tool only soft-deletes)

argus_update_fingerprint

Re-roll or override a profile's fingerprint

argus_fingerprint_check

Check a running profile's fingerprint

argus_list_proxies

List proxies

argus_create_proxy

Add proxy

argus_update_proxy

Update a proxy

argus_check_proxy

Check reachability and egress IP

argus_delete_proxy

Remove a proxy

argus_reimport_proxies

Re-import proxies from a list of rows

argus_assign_cookie_set

Set which profiles launch with a cookie-set

argus_unassign_cookie_set

Detach profiles from whatever cookie-set they hold

argus_list_cookie_sets

The workspace's cookie sets, metadata only

argus_update_cookie_set

Change a cookie set's name, status, colour, folder or tags

argus_trash_cookie_sets

Move cookie sets to Trash

argus_list_trashed_cookie_sets

The cookie sets currently in Trash

argus_restore_cookie_sets

Bring cookie sets back out of Trash

argus_purge_cookie_sets

Permanently delete cookie sets from Trash

argus_list_automations

List the org's automations, with step counts

argus_list_recipes

List the prebuilt recipes, and which ones this workspace has set up

argus_set_up_recipe

Create one prebuilt recipe, plus any tables it needs

argus_list_scrapers

The scraper catalogue, and what this workspace has run

argus_get_scraper

One scraper's form and the columns it produces

argus_sample_scraper

A dry run: one page, nothing written

argus_run_scraper

Run a scraper; returns a run id immediately

argus_scraper_runs

Past runs of one scraper, newest first

argus_automation_schema

The step catalogue: every step type, its fields and how they validate

argus_get_automation

Read one automation, including its full step tree

argus_create_automation

Create an automation. Steps are validated before anything is stored

argus_update_automation

Change an automation's name, description, steps or wiring

argus_delete_automation

Move an automation to Trash. It stops running on launch and on its schedule

argus_run_automation

Run an automation against a profile, launching it if needed

argus_automation_runs

Recent runs of one automation, with status and errors

argus_list_schedule_entries

Every scheduled workflow in the workspace

argus_create_schedule_entry

Create a scheduled workflow or AI task

argus_update_schedule_entry

Change a scheduled entry's time, steps, prompt, colour or enabled state

argus_delete_schedule_entry

Delete a scheduled workflow

argus_schedule_history

What the calendar actually ran over a range of days

argus_keep_awake

Whether this computer is being held awake for the schedule

argus_set_keep_awake

Hold this computer awake so scheduled runs are not missed

argus_schedule_notifications

Whether the signed-in user hears about their scheduled days

argus_set_schedule_notifications

Turn the schedule's Telegram messages on or off

argus_list_event_triggers

Every event trigger in the workspace

argus_create_event_trigger

Create an event trigger

argus_update_event_trigger

Change an event trigger's watch settings, target or enabled state

argus_delete_event_trigger

Delete an event trigger

argus_list_datasets

The workspace's datasets, with their declared columns

argus_create_dataset

Create a dataset, optionally with starting columns

argus_update_dataset

Change a dataset's name, icon, colour or folder

argus_update_dataset_schema

Replace a dataset's declared column list

argus_update_dataset_options

Edit one choice column's options

argus_sample_rows

A page of a dataset's rows

argus_query_rows

Query a dataset's rows by where conditions, optionally aggregated

argus_add_rows

Append rows to a dataset

argus_update_rows

Rewrite dataset rows in place by id

argus_delete_rows

Delete dataset rows by id or by a where filter

argus_trash_datasets

Move datasets to Trash

argus_list_trashed_datasets

The datasets currently in Trash

argus_restore_datasets

Bring datasets back out of Trash

argus_purge_datasets

Permanently delete datasets from Trash

argus_list_projects

The workspace's projects, what each holds, and the index of its brain

argus_project_context

One project's goal, brief and rules, plus the titles of its other documents

argus_delegate

Hand a goal to Argus's own orchestrator, inside a project's context

argus_list_connectors

The workspace's connectors, and the field list of every kind

argus_create_connector

Add a connector. Owner-only, like the Connectors view

argus_update_connector

Rename a connector, change its config or make it the default

argus_delete_connector

Delete a connector

argus_test_connector

Send a real test message, or a one-word AI completion

argus_list_folders

The folders profiles, proxies, cookie sets and automations are filed in

argus_list_statuses

Every status label a profile, proxy or cookie set can carry

argus_get_proxy_share_limit

This machine's proxy-sharing threshold

argus_set_proxy_share_limit

Change this machine's proxy-sharing threshold

argus_telegram_status

Whether the notification bot is set up, and who is subscribed

argus_set_telegram_pref

Subscribe the signed-in user to one automation's outcomes

argus_set_telegram_bot

Set the workspace's notification bot. Owner-only

argus_table_columns

What each table shows, and every column it could show

argus_set_table_columns

Show or hide columns on a table

argus_skills_schema

The vocabulary a skill is written in: tool packs, entry tabs, shelf ids

argus_list_skills

List the assistant's skills, built-in and custom

argus_get_skill

Read one skill, including its full brief

argus_save_skill

Create a custom skill, or edit a built-in one

argus_delete_skill

Delete a custom skill, or reset a built-in to its shipped brief

argus_trash_profiles

Move profiles to the trash

argus_list_trashed_profiles

Profiles currently in the trash

argus_restore_profiles

Restore profiles from the trash

argus_purge_profiles

Delete trashed profiles permanently

argus_switch_tab

Bring one of a profile's tabs to the front

argus_new_tab

Open a new tab in a launched profile

argus_page_recording

What has been done to this page so far

argus_save_page_recording

Save what was done to a page as an automation

argus_dedupe_rows

Remove duplicate rows

argus_search_automations

Find automations by name, step or connector

argus_automation_summary

What one automation does, without its full document

argus_schedule_day

One day of the calendar

argus_trigger_history

What has fired recently

argus_create_project

Start a project

argus_add_to_project

Put records into a project

argus_remove_from_project

Take records out of a project

argus_read_project_doc

Read one project document

argus_write_project_doc

Write a project document

argus_delete_project_doc

Delete a project document

argus_make_plan

Lay out a multi-step plan

argus_delegate_many

Hand several goals to subagents at once

argus_list_mailboxes

The mailboxes this workspace can read

argus_list_messages

List a mailbox folder

argus_read_message

Read one message

argus_read_new_message

Wait for a message that has not arrived yet

argus_open_compose

Start a draft

argus_list_compose

Drafts that are open right now

argus_set_compose_fields

Fill in a draft

argus_send_compose

Send a draft

argus_close_compose

Discard a draft

argus_list_docs

The knowledge-base index

argus_read_doc

Read one knowledge-base article

argus_search_docs

Search the knowledge base

argus_get_context

What this workspace actually holds

argus_recent_errors

What has gone wrong lately

16 drive a page directly, with no endpoint behind them

argus_connection_status

Confirm this MCP connection works, and say as whom

argus_page_snapshot

The interactive elements on a page, each with a selector to act on it

argus_click

Click an element, or a point, in a running profile's page

argus_type

Type into a field in a running profile's page

argus_press_key

Press a single key in a running profile's page

argus_scroll

Scroll a running profile's page

argus_wait_for

Wait until a page reaches a condition

argus_extract

Read values out of a running profile's page

argus_select_option

Choose an option in a dropdown

argus_list_tabs

List the open pages in a running profile

argus_navigate

Point a page at a URL and wait for it to settle

argus_go_back

Go back, or forward, in a page's own history

argus_reload

Reload a page and wait for it to settle

argus_read_page

Read a page's visible text, whole or by CSS selector

argus_screenshot

Screenshot a page — JPEG by default, PNG on request

argus_eval

Evaluate a JavaScript expression in a page and return its value

3 endpoints have no tool at all — the destructive and bulk ones. They are listed on the API reference, marked HTTP only.

Automation connectors

Connectors are the outside services an automation can reach: a model to ask, somewhere to send the answer, and somewhere for a run's rows to land. A step stores a connector id and nothing else, so a key changes in one place and every automation using it follows.

Twelve AI entries share exactly two wire protocols. Eleven speak OpenAI's chat-completions shape, because each of them publishes an OpenAI-compatible endpoint; Claude is the one that is genuinely different. Two of the twelve run on your own machine and need no key at all.

The data connectors are where the save rows and load rows steps point. Each one carries its own container as well as its credential — a Sheets connector holds the spreadsheet, an Airtable one the base — so a step only ever names a single table, tab, key or file.

The captcha connectors are what the solve captcha step buys an answer from. Two entries and two wire protocols again, because every service in that market copied one of them. This is the only category that spends money per call, so its Test reads the account balance and solves nothing — and one of the two, CapMonster Pro, runs on your own machine with no per-solve fee at all.

Connector credentials are stored in your workspace, readable by anyone in it who can open the connectors list — and returned in full over the local API, so an Argus API key is equivalent to the credentials it can read. Argus masks them in its own interface, but that is a convenience rather than a security boundary — give a connector the narrowest key the service will issue.

The new-connector picker listing twelve AI model presets, from ChatGPT and Claude to local LM Studio and Ollama, five messaging presets from Telegram to email over SMTP, and nine database and file presets from Supabase and Postgres to Notion, local files and Meta Lead Ads. — Every target an automation can reach: twelve AI model presets — hosted or local — five messaging presets, and nine databases and files.

Endpoint: http://127.0.0.1:1234/v1
Model: local-model
Needs: None — it runs on your machine

Ollama

OpenAI-compatible

Endpoint: http://127.0.0.1:11434/v1
Model: llama3.1
Needs: None — it runs on your machine

Other

OpenAI-compatible

Needs: Your own endpoint, and a key if it wants one

Anything that answers POST {base}/chat/completions. You supply the base URL.

Messaging

Where a notify step sends its message, and where a run tells you it finished. One adapter each: unlike model vendors, chat services never converged on a wire format.

Needs: Bot token and chat ID

From @BotFather. The bot must have messaged the chat once, or be in the group. Group ids are negative numbers.

Where to get a key

Slack

Needs: Incoming webhook URL

The URL is the credential — anyone holding it can post to the channel.

Where to get a key

Discord

Needs: Webhook URL

Where to get a key

Needs: Cloud API phone number ID, access token, and a recipient

Free-form messages only reach people who messaged this number in the last 24 hours; outside that window WhatsApp requires a pre-approved template.

Where to get a key

Email (SMTP)

Needs: Host, port, from and to — username and password where the relay wants them

Port 465 connects over TLS; anything else starts plain and upgrades with STARTTLS.

Databases and files

Where the saveRows step writes a run's results, and where loadRows reads a work list back out. Every write goes out from the launcher, never from the profile's page — so a row landing in your own database is not billed to an identity's proxy.

Supabase

Needs: Project URL and service role key

Use the service_role key, not the anon key — the anon key is subject to row level security and will usually insert nothing without a policy.

Where to get a key

Postgres

Needs: Host, database, user and password

TLS is verified by default. Managed databases that present a self-signed certificate need the “require” mode, which encrypts but does not verify.

Firebase

Needs: Service account project ID, client email and private key

The service account needs the Cloud Datastore User role. Firestore is schemaless, so columns are free text.

Where to get a key

Redis

Needs: Host — password, database number and TLS where the server wants them

Rows are appended to a Redis list as JSON documents, one entry per row, and read back in arrival order. Managed Redis (Upstash, Redis Cloud) is TLS-only — pick verify-full.

Google Sheets

Needs: Service account client email and private key, plus the spreadsheet

Share the spreadsheet with the service account’s address as an Editor — a service account has no access to a file until it is shared with it, exactly like a person.

Where to get a key

Notion

Needs: Internal integration token

Open each database you want to write to and connect the integration under ••• → Connections. The token alone sees nothing.

Where to get a key

Airtable

Needs: Personal access token and the base

The token needs data.records:read, data.records:write and schema.bases:read, and access to this base.

Where to get a key

Local file

Needs: A folder on this machine

csv opens in any spreadsheet app. jsonl appends one object per line and survives a crash mid-run; json rewrites the whole array each time.

Meta Lead Ads

Needs: Page or System User access token with leads_retrieval, plus the Page id

Read-only: leads load into automations and datasets; nothing is ever written back to Meta.

Where to get a key

Captcha solving

What the solveCaptcha step buys an answer from. The step reads the site key off the live page and injects the token back into it, but the request to the provider goes out from the launcher — so it carries neither the profile's proxy nor its cookies, and the provider is told the page's address and its site key and nothing else. This is the one category that spends money per call, so its Test reads the account balance rather than solving anything.

2Captcha

Needs: API key

Pay per solve. The page URL and its site key go to the provider from the launcher, not through the profile's proxy.

Where to get a key

CapMonster

Needs: A server URL, plus a client key for the cloud one

Two products behind one API: CapMonster Pro runs on your own machine at 127.0.0.1:9090 with no per-solve fee, while CapMonster Cloud is paid and needs the key.

Where to get a key

Email delivery

What the sendBroadcast step mails through, and the only step allowed to name one. Separate from messaging on purpose: a messaging connector tells you a run finished, this one sends email to other people. It leaves from the launcher's own connection rather than a profile's proxy — the workspace is talking to a vendor it holds an account with, not an identity acting on a site.

Which list may go through it is not a setting. Every provider's acceptable-use policy prohibits cold outreach, purchased lists and scraped contact data, and the penalty is the account rather than a bounce. Cold mail goes out over the sendEmail step and your own mailboxes instead, warmed and capped and routed through each identity's proxy.

Resend

Needs: API key, plus a From address on a domain you have verified with Resend

For lists that opted in. Resend's acceptable-use policy prohibits cold outreach and scraped contact data, so cold mail goes out over the Send email step and your own mailboxes instead. Test lists the domains that are actually verified — an unverified From is accepted by the API and then bounces.

Where to get a key

Email verification

What the verifyEmail step asks whether an address has a mailbox behind it. Four verdicts, and only one of them means send: a catch-all domain accepts everything including mail for boxes that are not there, so it comes back as risky rather than deliverable, and a vocabulary the build does not recognise comes back as unknown. A verifier that guesses yes is worse than none.

Run it before the first message rather than during the campaign. A hard-bounce rate is read directly by every mailbox provider and a sending domain's reputation cannot be turned back once it is spent — so the dead addresses at the top of an imported list cost you the messages at the bottom of it. This is the second category where Test could spend your money, so it reads the credit balance and checks nothing.

MillionVerifier

Needs: API key

Pay per address checked, from credits that do not expire. Test reads the remaining balance and verifies nothing.

Where to get a key

ZeroBounce

Needs: API key

The same check with a wider verdict vocabulary — it separates a spam trap and an abuse address from an ordinary bad one. Pay per address; Test reads the balance.

Where to get a key

Services Argus collects from

These are not connectors, and nothing on this list has a key to paste or an account to hold. They are scrapers — 29 prebuilt collectors, each pointed at one service's public pages, each returning one typed table. They run over plain HTTP with a real browser's TLS fingerprint and open no window, which is why a Maps search that used to take eight minutes now takes about six seconds.

Google

Google Keyword Ideas · Google Trending Now · Google Search Results · Google Trends · Google Maps

YouTube

YouTube Keyword Ideas · YouTube Search Results · YouTube Transcripts

Bing

Bing Keyword Ideas

Amazon

Amazon Keyword Ideas

Instagram

Instagram Profiles · Instagram Posts · Instagram Followers

LinkedIn Profiles · LinkedIn Companies · LinkedIn Company Posts · LinkedIn Posts · LinkedIn Post Comments

TikTok

TikTok Profiles · TikTok Profile Videos · TikTok Videos

X Profiles · X Posts · X Post Lookup

Shopify

Shopify Storefronts

Indeed

Indeed Jobs

Greenhouse

Greenhouse Job Boards

Ashby

Ashby Job Boards

Lever Job Boards

A card can sit inside a workflow as well as on its own tab — the Run scraper step — and it reaches an outside agent as argus_run_scraper, one of the 143 tools above. For a service with no card, an automation driving a real profile is the general answer.

Point an agent at it

Create a key in the launcher, connect your client, and the tools appear in it. The API itself stays on http://127.0.0.1:39219, where only your machine can reach it.

Read the API reference See the automation steps Download Argus