# AdvisorPro MCP connector

The AdvisorPro connector brings AdvisorPro leads, opportunities, content, knowledge and campaigns into Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent through one governed endpoint, with each person signed in as themselves and every call logged.

Source: https://elaichi.ai/connectors/advisorpro/

## Facts

| | |
| --- | --- |
| Application | AdvisorPro |
| Category | Marketing Automation |
| AI tools | 113 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once AdvisorPro is connected

- Which AdvisorPro leads changed status this week?
- Draft a market update post and schedule it for Thursday
- List opportunities stuck in the proposal stage for over a month

## Connect AdvisorPro in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick AdvisorPro.
2. Optionally set Share with, then press Connect.
3. Paste an AdvisorPro API key. One person generates a token in AdvisorPro and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which AdvisorPro tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## AdvisorPro MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## AdvisorPro MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## AdvisorPro MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## AdvisorPro MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## AdvisorPro MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect AdvisorPro to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a AdvisorPro tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with AdvisorPro through Elaichi

### Move a lead forward after the call

Sales. Ask the agent to find the lead in AdvisorPro and move it to the right status while the conversation is still fresh. No tab switching, no forgotten follow-up.

### See which opportunities have stalled

Sales. List the AdvisorPro opportunities sitting in one stage for too long, then move the ones that have progressed. The pipeline review takes minutes instead of an afternoon.

### Draft and schedule a week of posts

Marketing. Have the agent generate AdvisorPro content from a topic, review it, and schedule each piece for the days you choose. Bulk scheduling clears a whole week in one ask.

### Approve a batch with citations attached

Compliance. Pull the citations behind a piece of AdvisorPro content, check them, and bulk approve what passes. The audit log shows who approved what and when.

### Pull a scheduled post when markets move

Marketing. When news breaks, ask the agent to unschedule the AdvisorPro posts that no longer fit and publish a fresh update now.

### Keep the knowledge library current

Operations. Add new knowledge entries to AdvisorPro, update stale ones and deactivate anything out of date, so generated content draws on the right source material.

## Elaichi vs Zapier MCP vs Composio for AdvisorPro

All three can connect AdvisorPro to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over AdvisorPro tools | Allow or restrict single AdvisorPro tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per AdvisorPro call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect AdvisorPro to Claude?

Connect AdvisorPro in Elaichi, then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. AdvisorPro signs in with an API key, so you paste the key from your AdvisorPro account and the connection is live. There is no OAuth application to register and no client ID or secret to generate.

### Does AdvisorPro work with ChatGPT and Cursor as well as Claude?

Yes. Once AdvisorPro is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect AdvisorPro once and every client picks it up.

### What can an AI agent actually do with my AdvisorPro data?

An agent can look up a lead or opportunity in AdvisorPro, move a lead to a new status, move an opportunity to a new stage, and tell you what is sitting in the pipeline. It can draft content, pull the citations behind it, schedule, unschedule or publish posts, approve a batch at once, create a campaign and keep the knowledge library current. Short, concrete asks, like move this lead to qualified, work better than long sentences.

### Does connecting AdvisorPro give the AI access to every workspace?

No. The agent works inside the AdvisorPro workspaces and permissions of the person who signed in, so it only sees the leads, opportunities and content that person already sees. Elaichi can narrow that access with roles and restrictions, and it can never widen it.

### Can my team share one AdvisorPro connection?

Yes. One person connects AdvisorPro with the API key, shares the connection with a team in Elaichi, and nobody else ever handles the key. Each teammate still signs in to Elaichi as themselves, so the audit log names the person who moved a lead or published a post.

### Can I stop an agent from deleting or changing things in AdvisorPro?

Yes. Restrictions in Elaichi apply per action, so you can stop publishing content, deactivating knowledge or changing an opportunity stage in AdvisorPro for a role or for one person. A restricted action still shows in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to an AdvisorPro connection when someone leaves?

Offboarding someone in Elaichi ends their access to AdvisorPro through every client at once. A shared AdvisorPro connection keeps working for everyone else on the team. If you disconnect AdvisorPro in Elaichi, it is removed from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client in one step.

### Does the AdvisorPro MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. AdvisorPro is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for AdvisorPro?

Yes. Both let Claude, ChatGPT or Cursor use AdvisorPro. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every AdvisorPro call.

### How is Elaichi different from Composio for AdvisorPro?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to AdvisorPro: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 113 AdvisorPro tools

Every tool below is callable through https://api.elaichi.ai/mcp once AdvisorPro is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Get single AdvisorPro workspace by ID** (Get). Get a single AdvisorPro workspace by id. Returns: id, name, owner_user_id, onboarding_progress. Required: id.
- **List all AdvisorPro workspaces** (List). List AdvisorPro workspaces visible to the calling agent. Global agents see every workspace; workspace-scoped agents see only their bound workspaces. Returns: id, name, owner_user_id, onboarding_progress.
- **AdvisorPro leads update status** (Update). Update the lifecycle status of an AdvisorPro lead (e.g. active, nurtured, closed). Returns the updated lead record including id, status, and persona_tag. Required: params.id, params.status.
- **List all AdvisorPro leads** (List). List AdvisorPro leads scoped to the workspace, with optional filtering by status, persona_tag, or name/company search.
- **Get single AdvisorPro lead by ID** (Get). Get a single AdvisorPro lead by id. Required: id.
- **List all AdvisorPro opportunities** (List). List AdvisorPro opportunities (deals) scoped to the workspace, with optional filtering by status or pipeline stage. Returns: id, status, pipeline_stage. Max 200 results per call; defaults to 50.
- **AdvisorPro opportunities update stage** (Update). Move an AdvisorPro opportunity to a new pipeline stage. Returns: id, status, pipeline_stage. Required: params.id, params.pipeline_stage.
- **AdvisorPro content extract** (Action). Extract content excerpts from AdvisorPro — each including id, title, and a body snippet up to 1200 characters — for use in messaging or agent context. Returns: id, title, body. Optionally filter by params.id or params.search; max 20 excerpts (default 5).
- **AdvisorPro content generate** (Generate). Generate a fully grounded AdvisorPro content draft via KB grounding, reference-library, and signal citations. By default runs async and returns job_id immediately (poll agents.job_status); set async=false to block up to 4 min and receive content and citations. Required: params.angle.
- **AdvisorPro content citations** (Action). List every source cited in a generated AdvisorPro content item (signals, reference items, transcripts, published parents). Only sources the model actually cited in the final body appear. Returns: id. Required: params.id.
- **AdvisorPro content schedule** (Action). Schedule an AdvisorPro content item for publication via the engine selector (Taplio for LinkedIn or the built-in cron dispatcher). Creates a dispatchable calendar row. Returns: id, scheduled_for, status. Minimum lead time: 10 min (LinkedIn), 15 min (newsletter), 5 min (blog).
- **AdvisorPro content unschedule** (Action). Cancel a scheduled AdvisorPro content item, removing it from Taplio when Taplio owns the row or clearing the built-in cron dispatcher slot. Returns: id, status. Required: params.id.
- **AdvisorPro content publish now** (Publish). Immediately publish a content item in AdvisorPro using the configured engine (Taplio for LinkedIn or the built-in cron dispatcher). Returns the published content item including id, title, status, type, and channel.
- **AdvisorPro content bulk approve** (Approve). Bulk-approve pending content items in AdvisorPro by a list of ids, by campaign scope, or all pending items at once. Returns the approved content items including id, title, status, type, and campaign_id.
- **AdvisorPro content bulk schedule** (Action). Spread content items in AdvisorPro across a publishing cadence using Taplio or the built-in cron dispatcher. Returns the scheduled content items including id, title, status, channel, and updated_at.
- **List all AdvisorPro content** (List). List content items scoped to the workspace in AdvisorPro. Optionally filter by status, type, or keyword search over title and body. Returns: id, title, status, body, channel, campaign_id, created_at, updated_at.
- **Update a AdvisorPro knowledge by ID** (Update). Patch an existing knowledge item in AdvisorPro. Only the supplied fields are updated; unset fields are left unchanged. Returns the updated item including id, name, type, category, visibility, is_active, tags, and updated_at. Required: id.
- **AdvisorPro knowledge deactivate** (Deactivate). Soft-delete a knowledge item in AdvisorPro by setting is_active to false. The item remains in the workspace and is recoverable via update. Returns the deactivated item including id, name, is_active, and updated_at. Required: params.id.
- **AdvisorPro knowledge sync list** (Sync). Pull all knowledge items for offline vault sync in AdvisorPro, including deactivated tombstones. Returns each item with id, name, extracted_text, tags, metadata.links, is_active, and updated_at, ordered oldest-first. Optionally filter to items updated after a given timestamp via params.since.
- **AdvisorPro knowledge upsert** (Upsert). Batch create or update knowledge notes in AdvisorPro using optimistic concurrency. Notes whose base_updated_at is older than the stored value are reported as conflicts and skipped. Notes without a category are AI-classified unless classify is false. Returns the resulting knowledge items. Required: params.notes. Max 200 notes per batch.
- **List all AdvisorPro knowledge** (List). List active knowledge items in AdvisorPro scoped to the workspace. Optionally filter by category or search name/summary. Returns each item including id, name, type, category, summary, tags, and visibility. Max 200 results per call.
- **Get single AdvisorPro knowledge by ID** (Get). Get a single AdvisorPro knowledge base item by id, including extracted_text when available. Returns: id, name, category, summary, tags, content_url, extracted_text, visibility, is_active, user_id, updated_at. Required: id.
- **Create a AdvisorPro knowledge** (Create). Create a new knowledge base item in an AdvisorPro workspace. Returns: id, name, category, summary, tags, content_url, extracted_text, visibility, is_active, user_id, updated_at. Required: params.name, params.user_id.
- **Create a AdvisorPro campaign** (Create). Create a draft LinkedIn outreach campaign in AdvisorPro. The campaign starts in status 'draft'; use add_leads then launch to activate it. Returns: id, name, status, description, goal, sequence_id, sender_accounts, daily_send_limit, launch_stage, workspace_id, created_at, updated_at. Required: params.name.
- **AdvisorPro campaigns add leads** (Add). Attach leads to an AdvisorPro campaign. Upserts on (campaign_id, lead_id) and silently filters out leads from other workspaces. Returns: id, name, status, description, goal, sequence_id, sender_accounts, daily_send_limit, launch_stage, workspace_id, created_at, updated_at. Required: params.campaign_id, params.lead_ids. Max 1000 leads per call.
- **AdvisorPro campaigns launch** (Action). Launch an AdvisorPro campaign, setting its status to 'active'. Validates every sequence step against LinkedIn character limits (invitations ≤ 200 chars, DMs ≤ 8000, comments ≤ 1250) before allowing the transition. Returns: id, name, status, description, goal, sequence_id, sender_accounts, daily_send_limit, and 4 more. Required: params.campaign_id.
- **AdvisorPro campaigns pause** (Pause). Pause an active AdvisorPro campaign. In-flight steps finish but no new steps are dispatched. Returns: id, name, status, description, goal, sequence_id, sender_accounts, daily_send_limit, launch_stage, workspace_id, created_at, updated_at. Required: params.campaign_id.
- **AdvisorPro campaigns resume** (Resume). Resume a paused AdvisorPro campaign back to 'active' status. Has the same effect as launch. Returns: id, name, status, description, goal, sequence_id, sender_accounts, daily_send_limit, launch_stage, workspace_id, created_at, updated_at. Required: params.campaign_id.
- **AdvisorPro campaigns stats** (Action). Get full funnel analytics for one AdvisorPro campaign. Returns id plus a funnel metric attributes object covering leads enrolled, invites sent, accepts, messages sent, replies, positive replies, meetings booked, and derived rates. Required: params.id.
- **AdvisorPro campaigns events** (Action). List raw event log rows for one AdvisorPro campaign, ordered newest first, with optional filtering by event type and ISO timestamp lower bound. Returns: id, campaign_id, event_type, created_at. Required: params.id.
- **AdvisorPro campaigns health** (Action). Get execution health for one AdvisorPro campaign including watchdog status and reason, sequence run states with pause reasons and retry counts, and open watchdog findings. Returns: id, attributes. Required: params.id.
- **AdvisorPro campaigns list leads** (List). List leads enrolled in an AdvisorPro campaign with their enrolment status. Returns: id, campaign_id, lead_id, status. Required: params.campaign_id.
- **List all AdvisorPro campaigns** (List). List AdvisorPro campaigns scoped to the workspace, optionally filtered by status. Returns: id, name, status. Defaults to 50 results (max 200).
- **Get single AdvisorPro campaign by ID** (Get). Get a single AdvisorPro campaign by id. Returns the campaign record including its name, status, sender_accounts, daily_send_limit, launch_stage, sequence_id, and embedded stats. Required: id.
- **AdvisorPro analytics overview** (Action). Get an AdvisorPro workspace scorecard covering the outreach funnel and rates, content performance, and pipeline metrics for a configurable look-back window. Returns: impressions, engagement, pipeline. The look-back window defaults to 30 days via params.days.
- **AdvisorPro analytics list campaigns** (List). List every campaign in an AdvisorPro workspace, each scored on the outreach funnel, for side-by-side comparison. Returns: campaigns. Optionally scoped by params.days and params.limit (defaults to 25 campaigns).
- **AdvisorPro analytics list content** (List). List per-post performance analytics across every distribution channel in an AdvisorPro workspace. Returns: impressions, engagement, engagement_rate. Optionally scoped by params.days and params.limit.
- **AdvisorPro analytics report** (Action). Get a composite, report-ready analytics payload for an AdvisorPro workspace that backs the branded PDF report. Returns: summary, outreach_funnel, campaigns, top_content, revenue_impact. Optionally scoped by params.days.
- **AdvisorPro analytics export** (Export). Export an AdvisorPro workspace analytics dataset as CSV or JSON. Returns: document, filename. Available datasets via params.dataset: overview, campaigns, content, leads, pipeline (defaults to overview). Output format defaults to csv via params.format.
- **AdvisorPro safety limits** (Action). Get per-seat LinkedIn safety limits in AdvisorPro. Returns invites_sent, messages_sent, cooldown_state, and next_reset_at for each seat. Informational only — Core remains the sole enforcing gate.
- **AdvisorPro safety reads** (Action). Get LinkedIn read budgets in AdvisorPro across workspace-level, bulk, shared-pool, and per-account limits. Returns safe_bulk_import_size — the largest lead import that fits inside every active budget right now. Optionally scoped to a specific seat via account_id.
- **AdvisorPro safety cooldowns** (Action). Get active LinkedIn safety cooldowns in AdvisorPro from both the Core governor and the local backoff latch. Returns class, reason, and clear_at for each seat currently under a hold.
- **AdvisorPro safety check** (Action). Run an informational LinkedIn action preflight check in AdvisorPro for one seat. Returns allowed, blocked_reason, and retry_at. Never consumes or grants capacity. Required: params.account_id.
- **List all AdvisorPro signals** (List). List AdvisorPro market intelligence signals ordered newest first, workspace-scoped. Returns signal objects including id, title, signal_type, category, relevance_score, is_read, is_relevant, entities, themes, metadata, created_at, and updated_at. Max 200 results per call.
- **Get single AdvisorPro signal by ID** (Get). Get a single AdvisorPro signal by id, including its full metadata payload. Returns the signal object including id, title, signal_type, relevance_score, sentiment, why_it_matters, is_read, is_relevant, metadata, created_at, and updated_at. Required: id.
- **Create a AdvisorPro signal** (Create). Push an external signal into an AdvisorPro workspace's intelligence feed. Returns the created signal including id, title, signal_type, category, relevance_score, sentiment, is_read, is_relevant, metadata, created_at, and updated_at. Required: params.title, params.agent_name.
- **Update a AdvisorPro signal by ID** (Update). Patch editable fields on an AdvisorPro signal by id. Returns: id, workspace_id, title, agent_name, signal_type, category, url, source, summary, description, why_it_matters, recommended_action, sentiment, relevance_score, trigger_flags, entities, themes, publish_date, metadata, is_read, is_relevant, created_at, updated_at. Required: id.
- **AdvisorPro signals mark read** (Action). Toggle the is_read flag on an AdvisorPro signal to true, or set it explicitly. Returns the updated signal including id, title, signal_type, relevance_score, is_read, is_relevant, metadata, created_at, and updated_at. Required: params.id.
- **Delete a AdvisorPro signal by ID** (Delete). Permanently delete a market intelligence signal from the AdvisorPro workspace feed. Returns an empty 204 response on success. Required: id.
- **AdvisorPro voice set** (Set). Write the workspace Tone of Voice directive, its source label, and/or the apply-by-default toggle in AdvisorPro. Returns: directive, source, apply_by_default.
- ...and 63 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
