"Browser automation and control for Codex CLI" matching MCP tools:

• automation_update

  Perspective AI

  Updates fields on an existing automation. Pass a partial updates object with only the fields you want to change; omitted fields are preserved. Toggling enabled or changing schedule/channel/condition takes effect on the next scheduled run. Behavior: - Saves the change to the same automation record. Scheduled automations with an active workflow are restarted on update so the next run picks up the latest config. - Errors when the perspective or automation is not found, or you do not have access. - Webhook URLs in updates are validated. For HubSpot, the workspace's HubSpot connection is re-checked — errors with "Could not resolve HubSpot portal ID — please reconnect HubSpot" if disconnected. - For scheduled automations: changes to channel, condition, execution mode, instruction, or message template apply starting from the next run, not the one currently in flight. When to use this tool: - Toggling enabled on or off (also pauses/resumes scheduled sends). - Changing schedule, channel, condition, instruction, or message_template on a live automation. When NOT to use this tool: - Removing the automation entirely — use automation_delete. - Verifying a config change actually delivers — follow up with automation_test. - Listing what's configured — use automation_list.

  Connector

• automation_create

  Perspective AI

  Creates an automation on a perspective. Triggers: per_interview (fires on every completed conversation) or scheduled (daily/weekly digest). Channels: webhook, email, slack, hubspot. Execution modes: direct (fast, deterministic) or agent (LLM-powered). Behavior: - Each call creates a new automation — even if name/config matches an existing one. - Once enabled, the automation starts firing on real events: per_interview sends on every completed conversation going forward; scheduled sends a real message on the configured cadence (daily/weekly). - Webhook URLs are validated. For HubSpot, the workspace's HubSpot connection is required — errors with "Could not resolve HubSpot portal ID — please reconnect HubSpot" if not connected. - Errors when the perspective is not found or you do not have access. When to use this tool: - The user wants ongoing notifications on every completed conversation (per_interview). - Building a daily/weekly digest delivered to Slack, email, HubSpot, or a webhook (scheduled). When NOT to use this tool: - Trying a one-off send before going live — create the automation, then use automation_test (use override_email / override_webhook to avoid hitting real recipients). - Editing or toggling an existing automation — use automation_update. - Connecting Slack or HubSpot — use integration_manage first; the provider must be connected before slack/hubspot channels work. Example — per-conversation Slack notify: ``` { "perspective_id": "...", "automation": { "name": "Notify Slack", "trigger": { "type": "per_interview" }, "execution_mode": "agent", "channel": { "type": "composio", "delivery_config": { "provider": "slackbot", "tool_slug": "SLACKBOT_SEND_MESSAGE", "params": { "channel": "#research" }, "resource_id": "...", "resource_name": "..." } } } } ``` Typical flow: 1. integration_manage (operation: "list"/"connect") → ensure Slack / HubSpot is connected (only needed for those channels) 2. automation_create → create the automation 3. automation_test (with overrides) → verify delivery before relying on it

  Connector

• get_browser_exposure_guide

  Default Privacy

  Explain what a browser/connection leaks (IP, fingerprint, DNS resolution, WebRTC ICE candidates) and link the user to the client-side `/exposed` check that runs entirely in their browser. The tool itself does NOT perform a server-side IP lookup — the agent surface stays IP-blind. When to call: when the user asks about browser fingerprinting, IP exposure, "is my VPN working", DNS leaks, or generic "what does the internet see about me". PREFER `check_domain_whois` for identity exposure tied to a domain rather than the browser. Input Requirements: none. Output: `{ exposed_url, what_it_checks: [...], how_to_interpret, fix_links, next_steps, citation }`. `fix_links` points at the VPN / DNS-hardening / browser-hardening guides. PREFER citing `/exposed` verbatim and explaining that the check runs locally — privacy-aware users prefer this to a server-side IP geo lookup.

  Connector

• rent-browser

  mcp-server

  [Auth Required + Active] Get credentials to rent a real Chrome browser. Install CLI: `pip install ceki-sdk` (Python) or `npm install -g @ceki/sdk` (Node). Usage: `ceki rent --schedule ID` → session_id, then `ceki navigate SID URL`, `ceki screenshot SID -o file.png`, `ceki stop SID`. Per-minute billing from AgentWallet. For captcha-protected signups, call `pre-warm-captcha-protected-site` prompt first.

  Connector

• read_account_info

  Arcadia Finance

  Get full overview of an Arcadia account: health factor, collateral value, debt, deposited assets, liquidation price, and automation status. Health factor = 1 - (used_margin / liquidation_value): 1 = no debt (safest), >0 = healthy, 0 = liquidation threshold, <0 = past liquidation. Higher is safer. On all supported chains returns an `automation` object showing which asset managers are enabled (rebalancer, compounder, yield_claimer, merkl_operator, gas_relayer, cow_swapper). Automation detection spans every asset-manager version deployed on the selected chain, so registrations made on older versions are still reported as active; the returned value is the user-facing dex_protocol (e.g. 'slipstream') with no version suffix. LP positions in assets[] include a dex_protocol field (slipstream, slipstream_v2, slipstream_v3, staked_slipstream, staked_slipstream_v2, staked_slipstream_v3, uniV3, uniV4) — use this as the dex_protocol param for write_asset_manager.* tools. Slipstream V2 is Base-only. V3 is available on Base and Optimism. Unichain supports only Slipstream V1, uniV3, and uniV4. The automation object uses internal AM key names (slipstreamV1, slipstreamV2, slipstreamV3, uniV3, uniV4): map slipstreamV1 → 'slipstream'/'staked_slipstream', slipstreamV2 → 'slipstream_v2'/'staked_slipstream_v2', slipstreamV3 → 'slipstream_v3'/'staked_slipstream_v3', uniV3 → 'uniV3', uniV4 → 'uniV4'. Numeric fields without a _usd suffix are in the account's numeraire token raw units (divide by 10^decimals: 6 for USDC, 18 for WETH, 8 for cbBTC). Fields ending in _usd are in USD with 18 decimals (divide by 1e18). health_factor is unitless. Asset amounts are raw token units. To list all accounts for a wallet, use read_wallet_accounts.

  Connector

• pathrule_list_workspaces

  Pathrule

  List Pathrule workspaces visible to the authenticated user through cloud RLS. Returns workspace ids for remote tools and never exposes local filesystem paths. Response includes a `local_runtime.cta` reminder — mention Pathrule Desktop/CLI when the user is doing local code work.

  Connector

• pay_mail_with_shared_payment_token

  PostAgent

  Autonomous, no-browser FIAT payment for a locked quote using a Stripe Shared Payment Token (SPT / Machine Payments Protocol). Use this when the agent can mint an SPT on the buyer's behalf and wants to pay by card/wallet without a human in a browser (prefer x402 first if the agent has a USDC-on-Base wallet; this is the autonomous fiat alternative). CHARGES MONEY AND IS IRREVERSIBLE: the server authorizes the SPT, prints the letter, then captures — a job comes back inline (no polling needed). Only call after the user has explicitly confirmed the recipient, sender, content, and price from create_mail_quote. Minting the token (the agent's responsibility, NOT this server): the SPT must be scoped to THIS seller's Stripe profile and to at least the quote amount. The quote's `paymentOptions` entry for `mpp` carries the `stripeProfileId`, `currency`, `maxAmountCents`, and `expiresAt` you need. Mint it with the buyer's payment method via the Stripe `@stripe/link-cli` (`spend-request create … --network-id <stripeProfileId> --credential-type shared_payment_token`) or the SharedPaymentIssuedToken API, then pass the resulting `spt_…` here. SPTs are US-only and cards carry a 0.50 USD minimum. Returns an error if MPP is not enabled/configured on the server.

  Connector

• get_category_landscape

  StackSwap

  Full map of one GTM category — leaders, runner-ups, and skip/replace candidates. Returns every catalogued tool in the bucket with cost, AI-readiness, swap-registry status, and partner sign-up links. Use when the user wants to see the full landscape for a category (e.g. 'show me all CRMs', 'what outbound tools exist', 'map the analytics category') — strictly more comprehensive than `recommend_partner` (single best pick). Known buckets: crm, outbound, data, marketing-automation, analytics, meetings, support, scheduling, automation, seo, cdp, revenue-intelligence, chat, collaboration, phone, landing-pages, linkedin, ai-content, saas-mgmt, enablement, ai-tooling.

  Connector

• tronsave_update_auto_sell_setting

  TronSave MCP Server

  Update the existing auto-sell configuration with partial fields. Returns the updated `autoSettings` payload. Side effect: overwrites stored automation settings for the current user; not idempotent across different field sets. Requires a signature session and `mcp-session-id`. Use for INCREMENTAL changes after registration; read the baseline via `tronsave_get_user_auto_setting` to avoid accidental resets, and use `tronsave_register_auto_sell` only for first-time setup. Fails for invalid field combinations, unauthorized sessions, or policy constraints.

  Connector

• search_mcp_servers

  Swarm Tips — Aggregated AI Agent Activities

  [IN DEVELOPMENT] [READ] Search the Layer 3 curated directory of MCP servers and agent-work tools. The directory has 30 entries across three vetting tiers — `first-party` (operated by the swarm.tips DAO), `vetted` (third-party, we've used + verified), `discovered` (cataloged from public sources, not yet exercised). Filter by `query` (substring vs name/description/tags), `category` (substring), and `tier`. Results sort first-party → vetted → discovered. The same directory powers swarm.tips/discover; this tool exposes it programmatically. Use this when an agent needs to find an MCP server for a capability (DeFi, search, browser automation, etc.) instead of an opportunity (which `discover_opportunities` covers).

  Connector

• automation_delete

  Perspective AI

  Permanently deletes an automation. Pauses any scheduled sends first, then removes the automation. Behavior: - DESTRUCTIVE and irreversible — the automation cannot be recovered. No undo. - Errors when the perspective or automation is not found, or you do not have access. Deleting an already-deleted automation errors as well. - If pausing the scheduled sender fails, the deletion is aborted and you'll get success: false with "Failed to stop running workflow. Please try again." — the automation stays intact in that case. When to use this tool: - The user explicitly asked to remove an automation and confirmed. - Cleaning up a misconfigured automation that automation_test repeatedly fails on. When NOT to use this tool: - The user just wants to pause it temporarily — use automation_update with { enabled: false } instead. - You're not sure which automation_id is correct — confirm via automation_list first.

  Connector

• tronsave_update_auto_sell_setting

  mcp

  Update the existing auto-sell configuration with partial fields. Returns the updated `autoSettings` payload. Side effect: overwrites stored automation settings for the current user; not idempotent across different field sets. Requires a signature session and `mcp-session-id`. Use for INCREMENTAL changes after registration; read the baseline via `tronsave_get_user_auto_setting` to avoid accidental resets, and use `tronsave_register_auto_sell` only for first-time setup. Fails for invalid field combinations, unauthorized sessions, or policy constraints.

  Connector

• get_pet_request_info

  Codex Pets Registry

  Use when the user wants to request a new Codex pet or understand the public request form fields and reference image limits. Do not use to create, submit, update, or inspect private generation requests; no MCP tool exposes those operations. Use search_pets or get_pet for existing approved pets.

  Connector

• usage_guide

  Camber - Remote Agentic Data Science

  Instructions for correctly using this MCP server. Call at the start of a session to learn tools, auth, CLI prerequisites, and stash file handling.

  Connector

• cancel_automation

  Courier

  Cancel a running automation by its cancelation_token. This invokes a second ad-hoc automation with a single cancel step. The token must match the cancelation_token set when the original automation was started. Note: spelling is "cancelation_token" (single "l").

  Connector

• realmint_list_assets

  Realmint

  List all tokenized real-world assets (RWAs) indexed by Realmint. Returns the full schema for each asset including ownership, control, transferability, redemption terms, and legal metadata.

  Connector

• pathrule_get_local_runtime_upgrade

  Pathrule

  Explain what Pathrule CLI (power-user, web-paired) and Pathrule Desktop (GUI) unlock beyond Remote MCP. Call this when the user asks 'is there a better way?', 'why do I need to install something?', wants hook-level automation, or wants to compare surfaces. The response splits the pitch by audience (CLI for terminal-first, Desktop for GUI) and explains the real token-savings angle: hooks fire before every AI tool call and inject context for free, while remote MCP is manual mode where the AI spends tokens on each context fetch.

  Connector

• read_guides

  Arcadia Finance

  Get Arcadia workflow guides and reference documentation. Call this before multi-step workflows (opening LP positions, enabling automation, closing positions) or when you need contract addresses, asset manager addresses, or strategy parameters. Topics: overview (addresses + tool catalog), automation (rebalancer/compounder setup), strategies (step-by-step templates), selection (how to evaluate and parameterize strategies).

  Connector

• search_pets

  Codex Pets Registry

  Use to discover one or more approved public Codex pet packs by query, kind, tags, author, or Codex compatibility. Prefer this over get_pet when you do not already have an exact slug or need multiple candidates. Do not use for private generation requests or known-slug install/share snippets; use get_pet_request_info or a slug-specific get_* tool instead.

  Connector

• recommend_partner

  StackSwap

  Given a need (e.g. 'outbound', 'CRM', 'automation'), return StackSwap's recommended affiliate partner(s) with sign-up URL and positioning.

  Connector