MCP · AI assistants

Lynqu ships a hosted Model Context Protocol server, so AI assistants can work your Lynqu account by natural language. “log everyone I met at the expo as leads”, “move Acme to Negotiation and draft a follow-up”.

Server endpoints

Endpoint	Audience	Tools
https://api.lynqu.com/mcp/v2	Organizations (Business/Enterprise seats)	168 tools. Full B2B suite: leads and the people on them, segments, contacts, companies, campaigns, events, team, follow-ups and their performance, sent mail and replies, dashboards, automation, price book, deals and quotes, AI employees
https://api.lynqu.com/mcp/me	Individuals	10 tools. Personal cards, card analytics, profile, and explain-feature

Connect a client

Both endpoints speak streamable HTTP with OAuth. In any MCP-capable client (Claude, ChatGPT, Cursor, Windsurf, VS Code, …):

1. Add a new MCP server / connector and paste the endpoint URL.
2. Your browser opens a Lynqu consent page. Sign in and approve.
3. Done. No tokens to copy; the OAuth connection can be revoked from Lynqu at any time.

Desktop and CLI clients that register with a loopback redirect (http://127.0.0.1, any port) are supported out of the box.

Plans and permissions

• Connecting is open to any signed-in user.
• Running tools requires Pro+AI, Business + AI, or Enterprise (your plan or your org seat). A Business workspace without the AI add-on can connect but not run tools.
• On the organization server every tool call re-checks your org role and the org’s MCP policy (admins can restrict which roles may use the assistant, or set it read-only). The assistant can never see or do more than you can in the app.
• All three roles (admin, manager and employee) may use the assistant by default. Account executives are exactly who the toolkit is for: an employee can add contacts and leads, work their own pipeline and follow up on their own deals. What they see stays bounded by the same rules as the app: an employee’s assistant reads only their own book, and team, billing, pipeline and scoring configuration remain manager- or admin-only. Admins who want a narrower surface can drop roles in Integrations → MCP.

The same gate as the app

Every tool asks the question its screen asks. A tool is never the cheaper way in. The cases where that is easiest to get wrong:

Tool	Requires
get-event	The events capability, as the event page does
list-events	Any member. Without the events capability the answer is narrowed to the events that are live now (id, name, dates), which is what a rep at a booth needs
list-lead-scoring-rules	The lead-scoring capability
list-followup-templates	Any member. Returns team templates, your own personal ones and AI proposals, the same list the Templates page shows you
create-followup-template	The follow-ups capability for a team template. Any member for a personal one (scope: mine), while personal templates are switched on
send-followup-now	Edit access to the lead. The template must be a team template or one of your own; an AI employee’s proposal is never sent
get-followup-performance	Any member for their own emails (scope: me). team and member:{id} follow the Messages rules: managers see the people they manage, admins everyone. Grouping by AI employee is for managers and admins
list-outbox	Any member for their own mail (scope: mine). member, all, agents and agent are for managers and admins, over the people they may see
get-booking-report	The analytics capability
list-segments	Any member
create-segment, update-segment, delete-segment	The lead-management capability, as the Segments view does
get-segment-performance	The analytics capability and the analytics add-on, as the Segments tab does
list-booking-pools, get-booking-pool, create-booking-pool	The booking-management capability
bulk-update-leads (reassigning)	The lead-management capability
attach-leads-to-campaign	Any member. Without the campaign-management capability, only your own leads, to a live campaign you are a member of

Four more rules hold everywhere:

• get-dashboard-summary counts only the leads you can see. A department manager’s totals are their departments’, not the organization’s.
• list-team-members lists people. AI employees are not team members and are never returned.
• Card tools honour the organization’s MCP policy for organization cards. If an admin switched the assistant off or set it read-only, organization cards follow that setting, while your personal cards stay yours.
• On Enterprise a custom role changes what a tool allows in the same moment it changes what the app allows.

update-lead can also pause and resume automated follow-ups for one lead (follow_ups_paused). See follow-up sequences.

Follow-ups

Tool	Does
list-followup-templates	Team templates, your personal ones and AI employees’ proposals, each marked (is_personal, is_proposal, is_locked). scope narrows it to team, mine or member:{id}
create-followup-template	scope: team or scope: mine. With mine, overrides_template_id makes your version of a team template, which automated sends to your leads then use instead of the team text
send-followup-now	Sends one template to one lead, exactly as picked. It is cancelled at send time, like an automated email, if the lead is closed, paused, opted out, bounced, replied recently or already booked
get-followup-performance	Sent, delivered, opened, clicked, replied, booked and won, grouped by template, sequence, step, member, agent or segment, over days 30, 90 or 365, ranked by reply rate. segment_id narrows any grouping to one segment (0 = emails to leads in no segment). A/B variants appear as their own template rows, with is_variant, variant_weight and segment
list-outbox	What was sent, and the replies that came back (source: reply). Never message bodies

A personal version is refused when the team template is locked, when you already have one of it, past 20 personal templates, or while an admin has switched personal follow-ups off.

Performance and the outbox both carry replies_tracked. A row’s reply rate is replied over counts.reply_delivered, the delivered emails that carried reply tracking, and is null when there are none. When it is false, replies are not being collected, so a reply rate of 0 says nothing about whether anyone answered.

Building or editing a sequence, locking a team template or sequence, making or promoting a version, adding, weighting or promoting an A/B variant and the organization’s personal follow-ups switch are all in the app. No MCP tool writes them.

Segments

Segments are named sets of leads described by conditions, worked out each time they are used.

Tool	Does
list-segments	Every segment in order, with its conditions, how many of the leads you can see it matches now, and how many sequences, rules and template variants use it
create-segment	Name, color, description and conditions (the same condition keys the Segments editor offers). Up to 20 per organization
update-segment	Change any of those
delete-segment	Refused while a sequence, an automation rule or a template variant still uses the segment, or an in_segment() expression in a sequence, a rule or a lead scoring rule names it; the answer lists them
get-segment-performance	For the last days 30, 90 or 365: leads, won, win rate, won value, open pipeline, time to first response, follow-up sends, reply rate and meetings booked per segment, plus a “Not in a segment” row and, when emails went to a segment that was since deleted, a “Former segments” row, ranked by win rate from 20 decided leads. Money cells say when deals in another currency could not be converted. Takes organization_id like the other segment tools

Existing tools that take or return a segment:

• list-leads with segment_id returns the leads that match it.
• create-automation-rule and update-automation-rule take segment_id as the rule’s audience; the rule then runs only for leads in that segment.
• get-followup-performance groups by segment and filters with segment_id (above).
• list-automation-rules returns each rule’s segment_id (null means every lead).
• get-lead returns the lead’s segments, in segment order.
• list-followup-templates marks A/B variants with is_variant, variant_weight and segment_id. A variant is a team arm of a template test, not a personal version, and it cannot be sent by hand or picked as a rule’s or an event’s template.

A report puts each lead in the first segment it matches, in the segments’ order, so rows add up. A filter or an audience only asks whether a lead matches.

Records can be corrected, not just created

Records are captured with whatever is known at the time and completed later. An email found after the fact, a title that turned out to be wrong. Every noun an assistant can create, it can also edit:

• update-contact, alongside create-contact and get-contact
• update-lead for a lead’s own details
• update-lead-note to reword a note in place, keeping its author and its position in the timeline (a voice transcript is never rewritable, its text is a record of what was said)
• update-campaign for a campaign’s name, description, dates and budget
• manage-department to rename a department or move it under a different parent (admin only, the org chart is what department-scoped lead visibility is computed from)
• update-opportunity for a deal’s name, type, probability, expected close date and forecast category

Editing is deliberately narrower than creating in one respect: anything with its own rules keeps its own tool. Reassigning a lead goes through assign-lead, stage and won/lost through update-lead-stage, campaign membership through attach-leads-to-campaign, and a deal’s value through manage-deal-line-item, so that a deal’s total and its line items can never disagree.

…and removed

An assistant that can create a record it should not have created needs a way to take it back, or the only route out is the app:

• delete-lead and delete-company. Manager or admin. Both are archives, not erasures: a lead can be restored by an admin, and a deleted company’s leads, contacts and deals are kept and simply unlinked.
• delete-contact: manager or admin, because a contact is shared data that other people’s leads point at.
• delete-lead-note and delete-lead-document: your own by default, or anyone’s on a lead you can edit. Deleting a document frees the storage it was using.
• delete-opportunity. Renewals and upsells only. A lead’s primary deal follows the lead, so closing it out means moving the lead to a won or lost stage.

For two records of the same thing, merge rather than delete: merge-leads for people and merge-companies for accounts. Merging keeps both halves of the history; deleting one of them throws away whichever half it was holding. merge-companies called with no arguments lists the duplicate pairs the organization currently has, each side with its lead, contact and deal counts so it is clear which record to keep.

create-company will not make a second account for a domain or a name it already has on file. It fails and names the existing one instead. Assistants work through lists quickly, and nothing in the product announces a duplicate account until somebody opens the duplicates review tab.

Enriching a record

start-enrichment accepts five subject types. ai_contact and network are yours; lead, org_contact (a person on the organization’s roster) and company (an account) are organization-owned. They draw on the organization quota pool and require active membership.

Enrichment is confirm-before-save: start-enrichment returns a job, get-enrichment-job reports when it is ready, and nothing is written until confirm-enrichment accepts it. Applying is fill-empty. A value someone typed is never overwritten. Enriching a contact fills the person’s own record, including identity links such as LinkedIn; a lead created from that contact afterwards inherits them.

AI employees

AI employees act in-process and are never MCP callers themselves. Separately, five tools let a person check on and manage them over MCP:

Tool	Does	Requires
list-agents	List the AI employees hired by your organization: role, status, whether it’s still in its shadow trial, what it’s working on, and its 30-day results	Any member
get-agent-timeline	Read what one AI employee did and why: the tool, its risk tier, the matched rule, its stated rationale, and the outcome	Any member (raw tool arguments are admin-only)
list-handoffs	List work AI employees have handed back to a person, with the brief each one wrote	Any member. Defaults to your own; managers and admins can widen the scope
decide-agent-approval	Approve or reject one action an AI employee has parked, waiting on a human	Admins, or a custom role granted the AI-employees capability
get-sales-brief	Read the confirmed brief the AI employees work from: who the organization reaches (customers, partners or an audience) and the outcome it wants, what it offers, who fits, the booking link and the current offer	Any member

Picking up, resolving, or handing a handoff back to its agent, editing a parked action’s arguments before approving it, and drafting or confirming the sales brief are app-only, not exposed over MCP. A confirmed brief re-ranks every lead in the organization, so it stays with the admin form.

Product knowledge

Most tools answer “what do I have”. One answers “what is this”:

Tool	Does	Requires
explain-feature	Explain any Lynqu feature in the words you used: what it is, what it is for, where it lives, which plan or permission it needs, and whether you have it. Also defines the industry terms from our glossary	Any member, and any individual on /mcp/me

It describes features you cannot use as well as ones you can, and says which is which. What a feature is and which plan includes it are already public on our pricing pages; whether your workspace has it stays behind the tools below.

Workspace and admin

Seven org surfaces that no tool used to reach. All read only.

Tool	Does	Requires
list-brand-assets	Brand kits, email signatures and virtual backgrounds. Drafts are visible only to people who can manage branding	Any member with the branding-view capability
list-studio-recipes	The AI Studio recipes on offer, what each one builds, and whether your role can apply it	The Studio capability
list-field-policies	Which fields are hidden or locked, for which roles and departments. Use it to explain a missing field rather than reporting it empty	The field-policies capability. Managers see the default policy plus their own departments
list-integrations	CRM, Slack, Teams and connected assistants, with the health of each. Never returns tokens or secrets	Admins
get-ai-settings	Whether the Orb and MCP are switched on for the workspace, which roles may connect, and how much AI credit is left	Admins, or a custom role granted the AI-employees capability
list-audit-events	Who did what and when. Returns the actor, the action and the record, never the before-and-after values	Admins
get-billing-summary	Plan, tier, seats in use and active add-ons. No card details, invoices or payment identifiers	Admins

Applying a Studio recipe, uploading or deleting a brand asset, writing a field policy, connecting or repairing an integration, switching the AI surfaces on or off, exporting the audit log, and buying or cancelling anything are all app-only.

What assistants deliberately cannot do

A few actions are reachable in the app but have no MCP tool at all. These are not gaps waiting to be filled. They are actions where an assistant being talked into one is worse than the convenience is worth:

• Sending, accepting or declining a quote. Assistants can draft and edit a draft; the moment a quote reaches a customer or moves deal value, a person presses the button. A quote that has already been sent cannot be edited or deleted over MCP at all.
• Validating an event ticket. Marking an attendee present is something a door does, not an agent.
• Reading someone else’s pay. Compensation is admin-only to read and admin-only to write, one band stricter than performance data. A manager can see a rep’s numbers but never their plan.
• Reordering a board. Assistants can move a deal to another stage, or to a stage on a different pipeline, but where a card sits within its column is a human gesture on a board they cannot see.

Everything else follows your own permissions exactly.

MCP vs. REST API

	MCP	REST API
Consumer	AI assistants	Your own code
Auth	OAuth consent flow	API keys
Plans	Pro+AI, Business + AI, Enterprise	Business and up
Shape	168 task-level tools (10 on /mcp/me)	Resource endpoints

If you’re building an integration, use the REST API. If you’re wiring an AI assistant, use MCP.