GTM Otto
Self-driving LinkedIn prospecting: it sources, warms and invites daily. You approve every message.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"linkedin": {
"url": "https://agent.gtmotto.com/mcp"
}
}
}Remote endpoints
https://agent.gtmotto.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (21)
🟢gtm_whoami
Who this key belongs to, and what the workspace may do: org name, plan, subscription status, how many products and plays exist, and the LEAD METER (leads added this calendar month, the plan's cap, and what is left). Start here — the remaining lead allowance is the one number that changes what is worth proposing. Read-only.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_list_plays
Every play in the workspace with enough context to route on: which product it sells, whether it is active or paused, whether a LinkedIn seat is actually connected (`seatConnected: false` means the play cannot act, whatever its status says), and how its leads are spread across the pipeline stages. Read-only.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_show_play(playId)
ONE play in full — everything needed to judge it or copy it into a better one: goal and voice, the account's daily cap and working hours (shared by every play on the seat), the ICP facets, the five sourcing lanes with their config and last run, the autonomy ladder (which rungs run alone and which wait for a human), the LinkedIn seat, and today's used/cap for the seat plus this play's share. Read-only. Pass a playId from gtm_list_plays.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play to inspect."
}
},
"required": [
"playId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_play_stats(playId)
The play's Stats screen: the pipeline (leads sourced → warmed → invited → new connections → conversations started) over four windows — all time, last 30 days, last 7 days, last 24 hours — each windowed count paired with the window before it as a percentage delta. 'Conversations started' counts real replies, never the openers Otto sent. Read-only.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play to report on."
}
},
"required": [
"playId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_linkedin_status(playId)
The play's LinkedIn seat and today's headroom against the LinkedIn limits. States: `no_seat` (nothing connected — the play cannot act), `seat_broken` (the account was disconnected or deleted; the queue is parked until a human reconnects), `pending`, `classic`, or `sales_navigator` (which search backend the ICP compiles to). Read-only. Connecting a seat is a browser flow — link the human to the cockpit for it.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play whose seat to check."
}
},
"required": [
"playId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_estimate_icp(industries, locations, sizes)
How big an audience a CANDIDATE ICP would reach — '≈ N companies match' — before committing to it. Writes nothing: no play, no ICP row, no cache. Use it to iterate (propose facets → see 40 → widen the locations → see 900 → then create the play). Returns null when the data provider has no key configured, which is not an error. Needs a write-scoped key only because it rides the gateway's action channel.
Input Schema
{
"type": "object",
"properties": {
"industries": {
"type": "array",
"items": {
"type": "string"
},
"description": "e.g. ['SaaS', 'Fintech']"
},
"locations": {
"type": "array",
"items": {
"type": "string"
},
"description": "e.g. ['France', 'Benelux']"
},
"sizes": {
"type": "array",
"items": {
"type": "string"
},
"description": "Headcount bands, e.g. ['11-50', '51-200']"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡gtm_create_play(name, productId, websiteUrl, productName, goal, ...)
Create a fully-configured play in one call: the product (an existing productId, or a websiteUrl which seeds one and kicks its research), the play itself, the ICP facets, which sourcing lanes are on, the autonomy ladder and the caps. Three rules are enforced server-side and cannot be talked around. (1) `activate` DEFAULTS TO FALSE — turning a play on spends the month's lead quota and takes real actions from the user's own LinkedIn account, so hand the human the returned cockpit link and let them press go. (2) A play with no live LinkedIn seat stays a draft whatever you pass. (3) Autonomy rules are written ONLY for the steps you name; every step you omit keeps gtmotto's own default, which is 'wait for a human'. Lanes that need their own seeds (post_engagers, competitor_posts, account_list) are refused if switched on without them.
Input Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The play's name."
},
"productId": {
"type": "string",
"description": "An existing product. Omit to create one."
},
"websiteUrl": {
"type": "string",
"description": "Seeds a NEW product from this website and kicks its research."
},
"productName": {
"type": "string",
"description": "Defaults to the website's hostname."
},
"goal": {
"type": "string",
"description": "What a conversation from this play should reach."
},
"voice": {
"type": "string",
"description": "How the messages should sound."
},
"icp": {
"type": "object",
"properties": {
"titles": {
"type": "array",
"items": {
"type": "string"
}
},
"seniority": {
"type": "array",
"items": {
"type": "string"
}
},
"languages": {
"type": "array",
"items": {
"type": "string"
}
},
"industries": {
"type": "array",
"items": {
"type": "string"
}
},
"sizes": {
"type": "array",
"items": {
"type": "string"
}
},
"locations": {
"type": "array",
"items": {
"type": "string"
}
},
"exclude": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false,
"description": "The audience, as plain strings — the same seven fields the cockpit's ICP screen fills. gtmotto compiles them into a LinkedIn search and normalises odd labels itself ('Swiss' → Switzerland, 'Fintech' → Financial Services)."
},
"sources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string",
"enum": [
"people_search",
"competitor_posts",
"job_offers",
"account_list",
"post_engagers"
],
"description": "people_search: LinkedIn people search compiled from the play's ICP (+ optional free-text keywords). | competitor_posts: Post discovery: Otto searches LinkedIn daily for posts matching an intent, judges each, and takes who engaged. | job_offers: Hiring signal: companies posting a role → the buyers inside them. | account_list: Companies you name (names, websites or LinkedIn page URLs) → Otto finds your buyers inside each. | post_engagers: RETIRED — folded into competitor_posts.postUrls. Still runs on rows that exist; do not configure it on new plays."
},
"on": {
"type": "boolean"
},
"config": {
"type": "object",
"properties": {
"keywords": {
"type": "string",
"description": "people_search: extra free-text terms on top of the ICP query (alone, a complete search). job_offers: the role being hired, e.g. 'Head of Sales'."
},
"intent": {
"type": "string",
"maxLength": 1000,
"description": "competitor_posts only. What you are hunting, in the operator's own words and language — e.g. 'people struggling with manual LinkedIn prospecting'. Drives the search writer, the post scorer and the comment scorer."
},
"competitors": {
"type": "array",
"items": {
"type": "string"
},
"description": "competitor_posts only. Keyword ANCHORS — tools, brands, chores ('Sales Navigator', 'Waalaxy', 'prospects froids'). The fallback searches when no intent is set. Max 25."
},
"postUrls": {
"type": "array",
"items": {
"type": "string"
},
"description": "competitor_posts (and retired post_engagers): LinkedIn post URLs or urn:li:activity:… URNs to harvest as they are. Max 25."
},
"companies": {
"type": "array",
"items": {
"type": "string"
},
"description": "account_list only. One entry per company — a name ('Acme'), a website ('acme.io') or a LinkedIn page URL ('linkedin.com/company/acme-corp'). Max 100."
},
"commenters": {
"type": "boolean",
"description": "Post lanes: take the people who commented (default true)."
},
"reactors": {
"type": "boolean",
"description": "Post lanes: take the people who reacted (default true). Both off = refused."
},
"minReactions": {
"type": [
"number",
"null"
],
"description": "competitor_posts: reaction floor for FOUND posts ('skip the posts nobody saw'); null = any post. The UI offers 25/50/100/250."
},
"postedWithinDays": {
"type": [
"number",
"null"
],
"description": "job_offers: how fresh the posting must be, in days; null = any."
},
"postGate": {
"anyOf": [
{
"type": "number",
"minimum": 0,
"maximum": 100
},
{
"type": "null"
}
],
"description": "competitor_posts: post-relevance floor 0–100, or null for OFF (the default). 0 is not off — it still demands a model verdict."
},
"intentGate": {
"anyOf": [
{
"type": "number",
"minimum": 0,
"maximum": 100
},
{
"type": "null"
}
],
"description": "Post lanes: per-person intent (scored from their comment against `intent`) floor 0–100, or null for OFF (the default). 0 is not off — it still demands a model verdict."
},
"fitGate": {
"type": "string",
"enum": [
"strict",
"standard",
"loose",
"off"
],
"description": "How the ICP facets LinkedIn could not filter on are judged per person: strict = every unmapped facet must match; standard (default) = one match is enough; loose = role/seniority only (best for engager lanes); off = keep everyone the query returned. The ICP's `exclude` list is absolute at every level."
}
},
"additionalProperties": false
}
},
"required": [
"key"
],
"additionalProperties": false
},
"description": "The sourcing lanes to configure."
},
"autonomy": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string",
"enum": [
"visit",
"like",
"comment",
"invite",
"first_dm",
"follow_up",
"reply"
]
},
"auto": {
"type": "boolean"
}
},
"required": [
"key",
"auto"
],
"additionalProperties": false
},
"description": "Only the rungs you name are written. Omitted rungs wait for a human."
},
"dailyCap": {
"type": "number",
"description": "Actions per day, all kinds summed. Defaults to the seat's full LinkedIn allowance (145), so pass it only to throttle. ACCOUNT-level: sets the ceiling every play on this LinkedIn account shares, not a per-play budget."
},
"workingHours": {
"type": "object",
"properties": {
"start": {
"type": "string"
},
"end": {
"type": "string"
},
"tz": {
"type": "string"
}
},
"required": [
"start",
"end",
"tz"
],
"additionalProperties": false,
"description": "e.g. { start: '09:00', end: '18:00', tz: 'Europe/Paris' }. ACCOUNT-level, like dailyCap."
},
"activate": {
"type": "boolean",
"description": "Default false. True only starts it if a live seat is already connected."
}
},
"required": [
"name"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_sources_reference
THE REFERENCE for configuring sourcing lanes — read it before your first gtm_configure_source / gtm_set_source / gtm_run_source call. Every lane (people_search, competitor_posts a.k.a. Post discovery, job_offers, account_list, and the retired post_engagers), every config field with its meaning, default and cap, the fit/intent/post gates, what makes a lane runnable, how the 5-minute tick and the 24h cadence work, what a preview costs versus a run, and what this surface deliberately will not do. No backend call; safe to call any time.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_show_sources(playId)
All five sourcing lanes of a play, configured or not — the read to make before touching any of them. Per lane: `configured`, `on`, the parsed `config` (defaults filled), the cockpit's `summary` (null = needs setup), `blocked` (why it cannot run, judged without running: needs_config / icp_empty / null), last/next run and the last run's funnel, `addedToday`, `failures`, and the lane's memory — `accounts[]` with `found: true|false` per typed company on account_list, `harvestedPosts` on the post lanes, the cached `searches` the model wrote on Post discovery. Play level: `state` is the same verdict the cockpit shows when the Leads table is empty (no_sources / paused / draft / no_seat / seat_broken / icp_empty / needs_config / lead_quota / never_ran / no_results / provider_error / added_nothing / ok), plus provider, seat, ICP facet count and the month's remaining lead quota. Read-only.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
}
},
"required": [
"playId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_source_runs(playId, key, limit)
The run history of ONE lane, newest first — the funnel over time (scanned → dropped by fit → dropped by intent → added / duplicates / capped), the ICP facets LinkedIn could not filter on, and the provider's status and message when it refused. Use it to tell 'the query returns nobody' from 'everyone was already a lead' from 'LinkedIn is rate-limiting the seat'. Read-only.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
},
"key": {
"type": "string",
"enum": [
"people_search",
"competitor_posts",
"job_offers",
"account_list",
"post_engagers"
],
"description": "Which lane. people_search: LinkedIn people search compiled from the play's ICP (+ optional free-text keywords). | competitor_posts: Post discovery: Otto searches LinkedIn daily for posts matching an intent, judges each, and takes who engaged. | job_offers: Hiring signal: companies posting a role → the buyers inside them. | account_list: Companies you name (names, websites or LinkedIn page URLs) → Otto finds your buyers inside each. | post_engagers: RETIRED — folded into competitor_posts.postUrls. Still runs on rows that exist; do not configure it on new plays."
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 50,
"description": "Runs to return (default 10, max 50)."
}
},
"required": [
"playId",
"key"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴gtm_configure_source(playId, key, config, listMode, on)
Write a lane's settings — upload an account list, set the Post-discovery intent and anchors, change the job keywords, move a gate. MERGE semantics: only the fields you send change. Lists (companies, postUrls, competitors) REPLACE by default; pass listMode 'append' to add to what is there (deduped, case-insensitive). Caps: 100 companies, 25 posts, 25 anchors — what did not fit comes back in `truncated`. Unknown fields are refused. Saving creates the lane's row if it never had one (OFF, because configuring is not switching on), makes the lane due again immediately and resets its retry backoff; on account_list it also forgets the cached misses so unfound companies are looked up again. Pass `on: true` to switch it on in the same call — refused, with nothing saved, if the lane would still have nothing to run on. Nothing runs inside this call: an ON lane on an ACTIVE play runs on the next tick (≤5 min); otherwise use gtm_run_source. Read gtm_sources_reference for each field's meaning.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
},
"key": {
"type": "string",
"enum": [
"people_search",
"competitor_posts",
"job_offers",
"account_list",
"post_engagers"
],
"description": "Which lane. people_search: LinkedIn people search compiled from the play's ICP (+ optional free-text keywords). | competitor_posts: Post discovery: Otto searches LinkedIn daily for posts matching an intent, judges each, and takes who engaged. | job_offers: Hiring signal: companies posting a role → the buyers inside them. | account_list: Companies you name (names, websites or LinkedIn page URLs) → Otto finds your buyers inside each. | post_engagers: RETIRED — folded into competitor_posts.postUrls. Still runs on rows that exist; do not configure it on new plays."
},
"config": {
"type": "object",
"properties": {
"keywords": {
"type": "string",
"description": "people_search: extra free-text terms on top of the ICP query (alone, a complete search). job_offers: the role being hired, e.g. 'Head of Sales'."
},
"intent": {
"type": "string",
"maxLength": 1000,
"description": "competitor_posts only. What you are hunting, in the operator's own words and language — e.g. 'people struggling with manual LinkedIn prospecting'. Drives the search writer, the post scorer and the comment scorer."
},
"competitors": {
"type": "array",
"items": {
"type": "string"
},
"description": "competitor_posts only. Keyword ANCHORS — tools, brands, chores ('Sales Navigator', 'Waalaxy', 'prospects froids'). The fallback searches when no intent is set. Max 25."
},
"postUrls": {
"type": "array",
"items": {
"type": "string"
},
"description": "competitor_posts (and retired post_engagers): LinkedIn post URLs or urn:li:activity:… URNs to harvest as they are. Max 25."
},
"companies": {
"type": "array",
"items": {
"type": "string"
},
"description": "account_list only. One entry per company — a name ('Acme'), a website ('acme.io') or a LinkedIn page URL ('linkedin.com/company/acme-corp'). Max 100."
},
"commenters": {
"type": "boolean",
"description": "Post lanes: take the people who commented (default true)."
},
"reactors": {
"type": "boolean",
"description": "Post lanes: take the people who reacted (default true). Both off = refused."
},
"minReactions": {
"type": [
"number",
"null"
],
"description": "competitor_posts: reaction floor for FOUND posts ('skip the posts nobody saw'); null = any post. The UI offers 25/50/100/250."
},
"postedWithinDays": {
"type": [
"number",
"null"
],
"description": "job_offers: how fresh the posting must be, in days; null = any."
},
"postGate": {
"anyOf": [
{
"type": "number",
"minimum": 0,
"maximum": 100
},
{
"type": "null"
}
],
"description": "competitor_posts: post-relevance floor 0–100, or null for OFF (the default). 0 is not off — it still demands a model verdict."
},
"intentGate": {
"anyOf": [
{
"type": "number",
"minimum": 0,
"maximum": 100
},
{
"type": "null"
}
],
"description": "Post lanes: per-person intent (scored from their comment against `intent`) floor 0–100, or null for OFF (the default). 0 is not off — it still demands a model verdict."
},
"fitGate": {
"type": "string",
"enum": [
"strict",
"standard",
"loose",
"off"
],
"description": "How the ICP facets LinkedIn could not filter on are judged per person: strict = every unmapped facet must match; standard (default) = one match is enough; loose = role/seniority only (best for engager lanes); off = keep everyone the query returned. The ICP's `exclude` list is absolute at every level."
}
},
"additionalProperties": false,
"description": "The fields to change. See gtm_sources_reference."
},
"listMode": {
"type": "string",
"enum": [
"replace",
"append"
],
"description": "How list fields combine with the current value. Default replace."
},
"on": {
"type": "boolean",
"description": "Also switch the lane on/off. Omit to leave the switch alone."
}
},
"required": [
"playId",
"key",
"config"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡gtm_set_source(playId, key, on)
Switch a lane on or off — the toggle on the Sources list. Switching ON a lane that has nothing to run on (no companies, no intent/anchors/posts, no role) is refused: configure it first. An empty ICP is not a refusal — people_search may go on ahead of the ICP and comes back `blocked: icp_empty` until gtm_update_icp fills it. Switching OFF never fails and creates nothing. The lane then runs (or stops running) on the daily cadence; nothing runs inside this call.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
},
"key": {
"type": "string",
"enum": [
"people_search",
"competitor_posts",
"job_offers",
"account_list",
"post_engagers"
],
"description": "Which lane. people_search: LinkedIn people search compiled from the play's ICP (+ optional free-text keywords). | competitor_posts: Post discovery: Otto searches LinkedIn daily for posts matching an intent, judges each, and takes who engaged. | job_offers: Hiring signal: companies posting a role → the buyers inside them. | account_list: Companies you name (names, websites or LinkedIn page URLs) → Otto finds your buyers inside each. | post_engagers: RETIRED — folded into competitor_posts.postUrls. Still runs on rows that exist; do not configure it on new plays."
},
"on": {
"type": "boolean"
}
},
"required": [
"playId",
"key",
"on"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_preview_source(playId, key)
Dry-run ONE lane: '≈ N people match' and a 10-person sample, WITHOUT inserting a lead, spending the day's budget or moving the run clock. Same query, same gates, same scorers as a real run, on up to 50 people — so what it shows is what a run would keep. `size.precision` is honest: 'exact' (the query ran out inside the probe), 'atLeast' (the probe filled up; LinkedIn reports no total) or 'unavailable' (no seat, no config, paused play — `skipped` says which). Reports the ICP facets LinkedIn could not filter on (`unmapped`), facet values it had no id for (`unresolved`), which sampled people are `alreadyALead`, and on account_list what each company resolved to. Costs provider calls and, when a gate is on, model tokens. Refused on a paused play.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
},
"key": {
"type": "string",
"enum": [
"people_search",
"competitor_posts",
"job_offers",
"account_list",
"post_engagers"
],
"description": "Which lane. people_search: LinkedIn people search compiled from the play's ICP (+ optional free-text keywords). | competitor_posts: Post discovery: Otto searches LinkedIn daily for posts matching an intent, judges each, and takes who engaged. | job_offers: Hiring signal: companies posting a role → the buyers inside them. | account_list: Companies you name (names, websites or LinkedIn page URLs) → Otto finds your buyers inside each. | post_engagers: RETIRED — folded into competitor_posts.postUrls. Still runs on rows that exist; do not configure it on new plays."
}
},
"required": [
"playId",
"key"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴gtm_run_source(playId, key)
'Run once now' — run ONE lane immediately through the same code the sourcing tick runs, with force: an OFF lane still runs (that is what run-once means while configuring), a DRAFT play still runs (how you try a lane before launch), a PAUSED play does not. REAL: provider calls are made, leads are inserted, the play's daily budget and the org's monthly lead quota are spent. Only call it when the human asked for a run in this conversation; to look without spending, use gtm_preview_source. Returns the run's funnel (scanned / dropped / droppedIntent / added / duplicates / capped), the unmapped ICP facets, and `skipped` + `reason` when it could not run (no_seat, needs_config, icp_empty, daily_cap, lead_quota, no_results, provider_error).
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
},
"key": {
"type": "string",
"enum": [
"people_search",
"competitor_posts",
"job_offers",
"account_list",
"post_engagers"
],
"description": "Which lane. people_search: LinkedIn people search compiled from the play's ICP (+ optional free-text keywords). | competitor_posts: Post discovery: Otto searches LinkedIn daily for posts matching an intent, judges each, and takes who engaged. | job_offers: Hiring signal: companies posting a role → the buyers inside them. | account_list: Companies you name (names, websites or LinkedIn page URLs) → Otto finds your buyers inside each. | post_engagers: RETIRED — folded into competitor_posts.postUrls. Still runs on rows that exist; do not configure it on new plays."
}
},
"required": [
"playId",
"key"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴gtm_forget_harvested_posts(playId, key)
The tuning escape hatch for the post lanes. A post lane remembers every post it already paid to harvest so it never buys the same engagers twice — which makes it impossible to TUNE: change the intent or a gate, run, and the answer is 'no new posts since last time'. This clears that memory so the next run (or gtm_run_source) judges today's posts against the new settings. It COSTS: every forgotten post is a fresh engager fetch. Call it only after a deliberate settings change the human wants re-tested. Only competitor_posts and post_engagers have this memory.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
},
"key": {
"type": "string",
"enum": [
"people_search",
"competitor_posts",
"job_offers",
"account_list",
"post_engagers"
],
"description": "Which lane. people_search: LinkedIn people search compiled from the play's ICP (+ optional free-text keywords). | competitor_posts: Post discovery: Otto searches LinkedIn daily for posts matching an intent, judges each, and takes who engaged. | job_offers: Hiring signal: companies posting a role → the buyers inside them. | account_list: Companies you name (names, websites or LinkedIn page URLs) → Otto finds your buyers inside each. | post_engagers: RETIRED — folded into competitor_posts.postUrls. Still runs on rows that exist; do not configure it on new plays."
}
},
"required": [
"playId",
"key"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡gtm_update_icp(playId, titles, seniority, languages, industries, ...)
Change the ICP a play runs — the query behind people_search and the fit gate on every other lane. Seven string arrays, plain words (gtmotto normalises 'Swiss' → Switzerland, 'Fintech' → Financial Services itself): titles, seniority, languages, industries, sizes (headcount bands like '11-50'), locations, exclude ('never contact' — absolute). ONLY the facets you name change; the first write on a play forks its own ICP row from the product baseline (or a sibling play's row), so no other play's targeting is rewritten. Filling an empty ICP unblocks lanes parked on icp_empty and kicks the play's due lanes if it is active. Size a candidate first with gtm_estimate_icp.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
},
"titles": {
"type": "array",
"items": {
"type": "string"
}
},
"seniority": {
"type": "array",
"items": {
"type": "string"
}
},
"languages": {
"type": "array",
"items": {
"type": "string"
}
},
"industries": {
"type": "array",
"items": {
"type": "string"
}
},
"sizes": {
"type": "array",
"items": {
"type": "string"
}
},
"locations": {
"type": "array",
"items": {
"type": "string"
}
},
"exclude": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"playId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴gtm_update_play(playId, name, goal, voice, dailyCap, ...)
Change a play's own knobs — name, goal, voice — its two switches, and the ACCOUNT's pacing (daily action cap, working hours: shared by every play on the LinkedIn account, not per play). `paused: true` is the human's stop button (nothing runs, nothing is sent); `paused: false` resumes. `status: 'active'` LAUNCHES a draft; `status: 'draft'` takes it back off the road. Seat rule, enforced server-side: no live LinkedIn seat ⇒ neither launch nor resume makes it active — it stays/falls back to draft and the note says so. Launching or resuming kicks the play's due lanes at once. Only launch, resume or raise the cap when the human asked for it in this conversation: an active play spends the month's lead quota and acts from the human's own LinkedIn account. Does not touch the autonomy ladder.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play, from gtm_list_plays."
},
"name": {
"type": "string"
},
"goal": {
"type": "string",
"description": "What a conversation from this play should reach."
},
"voice": {
"type": "string",
"description": "How the messages should sound."
},
"dailyCap": {
"type": "number",
"exclusiveMinimum": 0,
"description": "Actions per day, all kinds summed. ACCOUNT-level: the ceiling every play on this LinkedIn account shares. Defaults to the seat's full LinkedIn allowance (145)."
},
"workingHours": {
"type": "object",
"properties": {
"start": {
"type": "string"
},
"end": {
"type": "string"
},
"tz": {
"type": "string"
}
},
"required": [
"start",
"end",
"tz"
],
"additionalProperties": false,
"description": "e.g. { start: '09:00', end: '18:00', tz: 'Europe/Paris' }. ACCOUNT-level, like dailyCap."
},
"paused": {
"type": "boolean",
"description": "true = stop everything; false = resume."
},
"status": {
"type": "string",
"enum": [
"active",
"draft"
],
"description": "'active' launches; 'draft' un-launches."
}
},
"required": [
"playId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_connect_linkedin(playId)
The link a human opens to connect (or reconnect) their LinkedIn account to a play — the one cockpit step the play cannot run without. Hand the URL to the human, tell them to say when it is done, then call gtm_linkedin_status: the seat reads `classic` or `sales_navigator` once bound. The link expires in 15 minutes; call again for a fresh one. Nothing is sent, nothing is read from their account by this call.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "The play to bind the seat to."
}
},
"required": [
"playId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢gtm_list_approvals(playId)
Every drafted action that waits for the human — an invite note, a first message, a follow-up, a reply or a comment the planner wrote — with the draft, the 'why now', the lead, and a cockpit link. One play, or the whole workspace when playId is omitted. Show each draft to the human before gtm_approve / gtm_reject; never decide for them. Read-only.
Input Schema
{
"type": "object",
"properties": {
"playId": {
"type": "string",
"description": "One play; omit for all."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴gtm_approve(approvalId)
Approve ONE drafted action by its approvalId (from gtm_list_approvals). It then leaves on the seat's next slot, inside LinkedIn's limits — this is the human's tap, moved from the cockpit to the chat, so ONLY call it after showing them the draft and getting a yes in this conversation. An already-decided card is refused.
Input Schema
{
"type": "object",
"properties": {
"approvalId": {
"type": "string",
"description": "The card to approve."
}
},
"required": [
"approvalId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴gtm_reject(approvalId)
Reject (skip) ONE drafted action by its approvalId. Nothing is sent; the planner records the decline and re-plans around it instead of proposing the same step again. Ask the human first, as for gtm_approve.
Input Schema
{
"type": "object",
"properties": {
"approvalId": {
"type": "string",
"description": "The card to reject."
}
},
"required": [
"approvalId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence