Adwarp

Adwarp

[npm] [License: MIT]

Website · Docs · Install guide · npm package

Adwarp (formerly Liam) is the open-source ad agent for LinkedIn Ads and Google Ads. Create campaigns by talking to Claude (MCP) or from a CLI. Built for go-to-market teams who want to spin up many campaigns from a contact list and a brief, then add creative images themselves. Everything starts switched off: LinkedIn entities are created as drafts and Google entities as paused. A LinkedIn campaign goes live only when you explicitly ask Adwarp to turn it on or switch it on yourself in Campaign Manager, and Google campaigns can only be switched on in the Google Ads UI.

Unofficial and not affiliated with or endorsed by LinkedIn or Google.

Covers creation, matched audiences (including building one straight from Salesforce or HubSpot), conversion selection, performance reporting/insights, competitor ad intelligence, and a change journal with before/after lift. See ROADMAP.md for what's shipped and what's planned next.

What you can do with it

Once Adwarp is connected, you talk to your assistant in plain language. Real requests it handles today, roughly in the order a campaign comes together:

• "How many VPs of demand gen at US SaaS companies can we reach?" (resolves targeting facets, estimates reach before any money is involved)
• "Upload this CSV as a matched audience." (auto-cleans columns, hashes emails, keeps names, companies and titles for LinkedIn's people match, converts company domains to URLs)
• "Build an audience from Salesforce: every contact on an account flagged as a target." (SOQL straight to a matched audience)
• "Turn our HubSpot target accounts list into a LinkedIn audience." (a HubSpot list or search straight to a matched audience of contacts or companies)
• "Launch a draft campaign for that audience, $100/day, tracking the demo-booked conversion." (campaign group + campaign + draft ads in one call)
• "What ads is our biggest competitor running right now, and what offers are they pushing?" (reads the public Ad Library: copy, formats, and EU targeting metadata for any company)
• "How did retargeting do last month vs the month before?" (trend report with deltas)
• "Which ads should I pause this week?" (account rollup with top/bottom performers and flags, then pauses the ads you pick, leaving the rest of each ad group running)
• "Rewrite the copy on the losing ad." (delete + recreate as a fresh draft; LinkedIn ignores edits to a live ad's post)
• "Did the new headline actually help?" (change journal + before/after lift)

Adwarp resolves the details and reports back the ids. Every capability is also an adwarp CLI command for scripted or batch use.

Put it on a loop

There is no scheduler in Adwarp. Use the one in whatever client you drive it from. Some loops that work well:

• "Every Monday at 9am, pull last week's performance summary, compare it to the week before, and flag anything that moved more than 20%." (a Claude Code scheduled agent)
• "Every Friday, check what new ads our top three competitors shipped this week and summarize the angles."
• "Check the audience match status every few hours and tell me when it clears 300 members." (the minimum for a matched audience to serve)
• Or skip the assistant entirely and put the CLI in cron: 0 9 * * 1 adwarp report summary -p last_7_days

Hierarchy mapping (the two platforms disagree)

LinkedIn's names are shifted one level from everyone else's, which is the single most common source of confusion when working across both:

So a LinkedIn "campaign" and a Google "campaign" are not the same thing: Google's campaign holds the budget and targeting (LinkedIn's campaign group plus campaign), and its ad group holds keywords.

Google Ads

Search campaigns only, creation-first. What is there today:

adwarp google auth loginadwarp google accounts list                       # proves the token and OAuth client workadwarp google keywords "revops automation" --url https://example.com/productadwarp google conversions listadwarp google launch --brief examples/google-brief.json           # dry runadwarp google launch --brief examples/google-brief.json --apply   # create it, pausedadwarp google campaigns listadwarp google report perf keyword -p last_30_days

A launch creates the budget, campaign, geo and language targeting, ad groups, keywords, and responsive search ads in one atomic mutate: it either lands whole or not at all, so a failure cannot leave half a campaign behind. Every write is validated server-side first, which is a genuine dry run rather than a local guess.

Three house rules are hard-coded, because all three default the wrong way in the UI and quietly waste B2B budget:

• Search network only. Display expansion and search partners off.
• Physical presence only. "US" means people in the US, not people anywhere who searched about it.
• Manual CPC to start. Smart bidding with no conversion history spends unpredictably. Switch in the UI once there is data.

Setup

Google Ads needs two things LinkedIn does not:

1. A developer token, from a Google Ads manager (MCC) account at ads.google.com/aw/apicenter. A plain client account cannot issue one. Approval usually lands on Explorer access automatically (2,880 production ops/day).

   Explorer is not enough for adwarp google keywords. Explorer blocks KeywordPlanService, so keyword research needs Basic access (15,000 ops/day), which is a separate application on the same screen. Campaign creation and reporting work fine on Explorer.

2. An OAuth client, from a Google Cloud project with the Google Ads API enabled. Use the "Desktop app" type, which accepts any localhost redirect.

   For the consent screen, do not leave it in "Testing". That status issues refresh tokens that stop working after 7 days. Beyond that it is a trade:

   • Internal (Workspace orgs only) is what Google's OAuth docs recommend for a single-company tool. Simplest, no verification, no 7-day expiry.
   • External + In production is the precondition for brand verification, the pilot that cuts Basic Access review from days to hours. The cost is that auth/adwords is a sensitive scope, so a published external app can require full OAuth app verification, potentially slower than the wait it saves.

   Internal is the better default for an internal tool. Choose External only if the fast track is worth the verification risk.

Then write ~/.adwarp/google.json:

{  "clientId": "....apps.googleusercontent.com",  "clientSecret": "...",  "developerToken": "...",  "loginCustomerId": "1234567890",  "defaultCustomerId": "0987654321",  "defaultConversionActionNames": ["Demo Booked"]}

loginCustomerId is the manager account and is only needed when you reach the target account through one. Run adwarp google auth login and you are set. Set up Google Ads in the docs has the same steps, plus the ADWARP_GOOGLE_* environment variables.

Packages

• @adwarp/shared: the platform-neutral layer: OAuth, credential stores, retry policy, the change journal, period and KPI math.
• @adwarp/core: LinkedIn REST client, resource modules, CSV + SHA256 hashing, Salesforce and HubSpot readers.
• @adwarp/google: Google Ads REST client, GAQL reads, atomic mutate builder, Search campaign creation.
• @adwarp/mcp: MCP server (stdio for local; reused by the hosted app). Primary interface.
• @adwarp/cli: the adwarp CLI over the same engines, for scripted batch runs.
• @adwarp/web: Next.js app that hosts the MCP over HTTP on Vercel, at https://mcp.adwarp.dev/api/mcp. It serves no pages: its other paths redirect to adwarp.dev.
• adwarp: the published npm package. Bundles the CLI and the MCP server behind the adwarp, adwarp-mcp and liam commands.

How it works

Both interfaces are thin layers over the same engine. Every MCP tool and CLI command builds a client via createLinkedInAds() (core/src/client.ts), which loads config plus an auto-refreshing OAuth token provider, then calls a typed resource module (campaigns.ts, audience.ts, report.ts, ...) that wraps LinkedIn's versioned REST API (LinkedIn-Version pinned in config). Input shapes live as zod schemas in core/src/schemas.ts and are reused verbatim as the MCP tool input schemas, so the CLI and MCP can never drift apart.

The drafts-first safety rule is enforced at creation: campaign groups, campaigns, and creatives default to DRAFT status, and going live is always an explicit request (a status of ACTIVE, campaigns update --status ACTIVE --apply, or ad resume --apply). On Google, no create schema can express an enabled status at all. Every write also passes through one HTTP chokepoint that appends to a local change journal (~/.adwarp/changelog.jsonl) for later lift analysis.

AGENTS.md has the full architecture notes and the LinkedIn API gotchas (restli encoding, required fields, DMP audience flow) learned from live testing.

Install

The install guide on adwarp.dev has these steps too, with a setup page for each client: Claude Code, Claude Desktop, Cursor, Codex, Gemini, the CLI, and, through your own endpoint, Meta Muse and Grok Bot.

There are two ways to install Adwarp:

1. As an MCP server, registered with Claude Code, Claude Desktop, Cursor, Codex, or other MCP clients that can run a local server, so you create campaigns by talking to your assistant. Run it locally, or skip the always-on install entirely and connect to the hosted endpoint with your own credentials.
2. As a terminal CLI, a global adwarp command for running everything from your terminal, scripts, or cron.

Both run against your own LinkedIn developer app, so your credentials and your ad account stay yours. Both come from the same npm package, adwarp. The first two steps are shared: create a LinkedIn app (step 0) and authenticate (step 1). After that, pick your path, or do both; they read the same ~/.adwarp credentials.

Step 0: create a LinkedIn app (once)

1. Create an app at https://www.linkedin.com/developers/apps. It must be associated with your company's LinkedIn Page.

2. On the Products tab, request access:

   Product	Needed for	Required?
   Advertising API	campaigns, ads, targeting, reporting, conversions	Yes
   Audiences	uploading CSV contact/company lists as matched audiences	Only for audience upload
   LinkedIn Ad Library	competitor ad metadata via the official API	Required for competitor discovery; no browser fallback

3. On the Auth tab, add http://localhost:53682/callback as an authorized redirect URL, and note your Client ID and Client Secret.

4. Once the Advertising API is approved, map your ad account under Products → Advertising API → View Ad Accounts. Skip this and accounts list comes back empty.

OAuth scopes. adwarp auth login requests rw_ads (create and edit campaigns), r_ads_reporting (reporting), rw_conversions (conversion tracking), and w_organization_social (image ads create a post owned by your LinkedIn Page). If you add a product or scope later, run auth login again; a token refresh keeps only the scopes you originally granted.

Step 1: authenticate (once, both paths)

Requires Node.js 20+.

# App credentials (alternatively set ADWARP_LINKEDIN_CLIENT_ID / ADWARP_LINKEDIN_CLIENT_SECRET env vars)mkdir -p ~/.adwarpecho '{ "clientId": "...", "clientSecret": "...", "linkedinVersion": "202605" }' > ~/.adwarp/config.json
npx -y adwarp auth login      # opens the browser; tokens land in ~/.adwarpnpx -y adwarp accounts list   # verify, then set defaultAccountId in config.json

Option 1: install as an MCP server

Register the server with your MCP client; it reads the ~/.adwarp credentials from step 1.

Claude Code

claude mcp add adwarp -- npx -y adwarp mcp

Claude Desktop, Cursor, or other MCP clients that can run a local server, in the client's MCP config JSON:

{  "mcpServers": {    "adwarp": { "command": "npx", "args": ["-y", "adwarp", "mcp"] }  }}

adwarp mcp and the adwarp-mcp command start the same server. Prefer Docker? The root Dockerfile builds an image of the same server; see Run it in Docker.

Ask for something read-only to confirm it works: "List my ad accounts" or "How did my account do in the last 30 days?"

Hosted MCP: connect with your own credentials, nothing to deploy

The hosted MCP server at

https://mcp.adwarp.dev/api/mcp

is multi-tenant, bring-your-own-credentials: you pass your LinkedIn developer app's details as request headers, and every call runs against your app and your ad account. The server holds no state for you: credentials are used in memory to call LinkedIn and never logged or persisted. The original address, https://liam-mcp.vercel.app/api/mcp, still works and serves the same endpoint, so existing connections need no change. The hosted endpoint docs have the full reference.

Do step 0 and step 1 above once (the LinkedIn app and the local auth login; LinkedIn's OAuth consent has to happen in your browser, so the token mint is the one local step). Then print the ready-to-run connect command:

npx -y adwarp auth export --mcp# claude mcp add --transport http adwarp https://mcp.adwarp.dev/api/mcp \#   --header "X-Adwarp-Linkedin-Client-Id: …" \#   --header "X-Adwarp-Linkedin-Client-Secret: …" \#   --header "X-Adwarp-Linkedin-Refresh-Token: …" \#   --header "X-Adwarp-Linkedin-Account-Id: …"

Other MCP clients that can send custom headers connect the same way (for clients without native HTTP transport: npx mcp-remote <url> --header "X-Adwarp-Linkedin-Client-Id: …" …). Verify with a read-only call ("list my ad accounts"), and from then on the connection is just a URL plus headers, usable from machines that never cloned this repo.

Know the trade-off: your client secret and refresh token travel with every request to that server, so only point them at a deployment you trust, or self-host the identical endpoint (next section). The same scopes that manage ads can also switch them on, so treat these credentials like an ad account password.

Hosted limitations (all by design, they need local resources): upload_audience_csv reads a CSV path on the server, audience_from_salesforce needs your local sf CLI, audience_from_hubspot is not registered there (its HubSpot token stays on your machine), competitor-ads scraping falls back to API-only metadata (no browser), and the change journal / lift tools need the local ~/.adwarp/changelog.jsonl. Run those through the local MCP server or CLI.

Put a skill on top. The clean split for teams: your MCP client's config holds the credentials (the headers above), and a small skill or system prompt holds your playbook: default ad account, naming conventions, standing exclusions, house rules like "audience expansion always off". The paid ads skills are working examples; copy one, swap in your defaults, and your assistant drives the hosted tools with your rules. Credentials never belong in a skill file.

Self-host the same endpoint on Vercel

Run your own instance so credentials never touch shared infrastructure, and so you also get a private env-configured tenant:

1. Get your env values locally: npx -y adwarp auth export.
2. Deploy apps/web to Vercel (set the project Root Directory to apps/web).
3. In Vercel project settings, add the env vars that auth export printed (ADWARP_LINKEDIN_CLIENT_ID, ADWARP_LINKEDIN_CLIENT_SECRET, ADWARP_LINKEDIN_REFRESH_TOKEN, ADWARP_LINKEDIN_VERSION, and a strong MCP_AUTH_TOKEN). In Vercel's Deployment Protection settings, disable Vercel Authentication for production (or add a protection-bypass secret); otherwise MCP clients can't reach the endpoint.
4. Your MCP endpoint is https://<your-app>.vercel.app/api/mcp. Connect with the secret in the header:

claude mcp add --transport http adwarp https://<your-app>.vercel.app/api/mcp \  --header "Authorization: Bearer <MCP_AUTH_TOKEN>"

Requests carrying MCP_AUTH_TOKEN use the env credentials (your tenant). Requests carrying the X-Adwarp-Linkedin-* headers above use the caller's credentials instead, so one self-hosted instance can serve your whole team, each member on their own LinkedIn app. The app serves only the endpoint. Its other paths, such as / and /docs, redirect to adwarp.dev.

Option 2: install the terminal CLI

Install the package globally for an adwarp command, or run any single command with npx -y adwarp <command>:

npm install -g adwarpadwarp accounts list

Coming from Liam? liam still works as an alias for adwarp: the package installs both names, so existing scripts and cron jobs keep running.

A sensible first session:

adwarp targeting search titles "demand generation"   # resolve targeting URNsadwarp report summary -p last_30_days                # account rollup + flagsadwarp launch --brief examples/brief.json            # creates DRAFTS only

The full CLI reference is below.

From source

For contributors, or to run changes that are not released yet. Requires git and pnpm too.

git clone https://github.com/adwarp-dev/adwarp.gitcd adwarppnpm install && pnpm -r build
node packages/cli/dist/index.js accounts listclaude mcp add adwarp -- node /abs/path/adwarp/packages/mcp/dist/index.js

Or paste this prompt and let your assistant do the setup

Copy the whole block into Claude (or any capable assistant with terminal access) and it will walk you through everything above, one step at a time:

You are helping me set up Adwarp, an open-source LinkedIn Ad Manager fromhttps://github.com/adwarp-dev/adwarp. It runs locally as an MCP server and a CLI,both from the npm package "adwarp".Everything it creates on LinkedIn starts as a draft, so nothing spends money until Iexplicitly turn it on.
Walk me through the setup one step at a time. Run commands for me where you can,show me exactly what to click where you cannot, and wait for my confirmationbefore moving to the next step.
1. Check that Node.js 20 or newer is installed. Help me install it if it is   missing.2. Help me create a LinkedIn developer app at   https://www.linkedin.com/developers/apps (it must be associated with my   company's LinkedIn Page):   a. On the Products tab, request access to the "Advertising API" product.      This is the only required product; approval can take a while.   b. Optional: also request "Audiences" if I want to upload CSV contact or      company lists as matched audiences.   c. Optional: also request "LinkedIn Ad Library" if I want competitor ad      metadata through the official API.   d. On the Auth tab, add http://localhost:53682/callback as an authorized      redirect URL, and show me where the Client ID and Client Secret live.3. Create ~/.adwarp/config.json containing my clientId, clientSecret, and   "linkedinVersion": "202605".4. Run "npx -y adwarp auth login". My browser opens LinkedIn's   consent screen; after I approve, tokens are stored in ~/.adwarp/credentials.json.5. Verify with "npx -y adwarp accounts list". If no accounts   show up, remind me to map my ad account in the Developer Portal under   Products > Advertising API > View Ad Accounts. Then set my account id as   "defaultAccountId" in ~/.adwarp/config.json.6. Register the MCP server with the assistant I use:   - Claude Code: claude mcp add adwarp -- npx -y adwarp mcp   - Claude Desktop or another client: add {"command": "npx", "args":     ["-y", "adwarp", "mcp"]} under mcpServers in its config.7. Confirm the tools load, then show me one read-only call working, for example   list_ad_accounts or a last_30_days performance summary.
If any step fails, show me the exact error and fix it with me before moving on.

Skills

The 17 paid ads skills turn Adwarp's tools into playbooks: what to pull, how to judge it, the thresholds that matter, and a report that ends in ranked actions. They also run from a CSV export with no Adwarp install. Analysis skills only read; the ones that change an account create drafts or paused entities after you confirm.

• LinkedIn Ads: account audit, performance review, spend analysis, lead drivers, pause rules, audience sizing, audience ops, ABM builder, guarded launch, Ad Library teardown
• Google Ads: account audit, search campaign builder, search terms
• Both platforms: weekly report, daily health check, experiment lift, budget pacing

npx skills add adwarp-dev/paid-ads-skills

The 11 adwarp-* skills that used to live in skills/ moved there under new names. Their folders now point to the new skills, so existing installs keep working. The full list of moves is in the skills docs.

Tools (MCP)

The tool reference lists every tool with its inputs and whether it works on the hosted endpoint.

• Accounts: list_ad_accounts
• Targeting: list_targeting_facets, search_targeting (typeahead a facet for entity URNs), list_facet_entities, estimate_audience (structured spec). Talk in plain language ("VPs of demand gen at SaaS companies in the US") and Adwarp resolves the facets and estimates reach before building the campaign.
• Audiences: upload_audience_csv (auto-cleans the CSV: normalizes column names, drops non-matcher columns, hashes emails, converts company domains to website URLs; supports both contact and company lists), audience_from_salesforce (SOQL to matched audience), audience_from_hubspot (HubSpot list or search to matched audience, local only), get_audience_status
• Conversions: list_conversions (select an existing insight-tag conversion to track). create_campaign and launch_from_brief accept conversionIds or conversionName, and fall back to defaultConversionName from config.
• Campaigns: create_campaign_group, create_campaign, create_text_ad, create_image_ad; list_campaigns (the account structure: campaign groups and their ad groups, drafts included, unlike reporting which only shows entities with spend), list_ads, delete_ad (removes the creative and best-effort its Direct Sponsored Content post), update_ad (pause, resume, or archive a single ad; ACTIVE starts spend, so it is set only on an explicit request). LinkedIn's editor ignores post edits on a live ad, so to change copy you recreate: delete_ad + create_image_ad.
• Orchestrator: launch_from_brief (audience + group + campaign + draft creatives in one call)
• Reporting: performance_summary (account rollup + top/bottom + flags), get_performance (per-entity KPIs at any level), performance_trend (weekly/monthly with deltas). KPIs: CTR, CPC, CPM, CPL, conversion rate, cost per conversion. Levels: campaign_group, campaign, creative.
• Competitor intel: inspect_competitor_ads uses the official Ad Library API for metadata and, in auto mode, an optional remote worker for creative copy and screenshots. No CLI or MCP code launches a local browser or falls back to scraping when the API fails. Supply both advertiser and companyId to filter broad API matches before queuing creatives. api mode is metadata only. auto queues at most 10 ads and returns cached results or job status; use get_competitor_creatives / adwarp creative-status <ids> to read completed jobs. The worker persists its cache, queue, rolling budgets and block state. See Remote creative worker for deployment and configuration.
• Change journal & lift: log_ad_change (record a change), list_ad_changes, compute_lift (before-vs-after performance for each recorded change). Adwarp auto-journals every change it makes; see Change journal & lift below.

Targeting spec

Structured targeting uses short facet names mapped to entity URNs (resolve URNs with search_targeting). URNs within a facet are ORed; facets are ANDed; excluded facets are ORed.

{ "include": { "locations": ["urn:li:geo:103644278"], "seniorities": ["urn:li:seniority:7"], "titles": ["urn:li:title:26587"] },  "exclude": { "industries": ["urn:li:industry:47"] } }

CLI reference

All commands also work via npx -y adwarp <cmd>. The CLI docs have the full list, including the Google Ads commands.

adwarp auth login                         # OAuth, stores tokens in ~/.adwarpadwarp auth export                        # print env vars for a self-hosted (Vercel) serveradwarp auth export --mcp                  # print the hosted-MCP connect command with your headersadwarp accounts list                      # list accessible ad accountsadwarp targeting search <facet> <query>   # typeahead a facet for entity URNsadwarp targeting estimate <facet> <urns…> # audience size for one facet's URNsadwarp audience upload -n <name> -f <csv> # clean + upload a CSV as a matched audienceadwarp audience upload -n <name> -f <csv> --dry-run   # preview the cleaned CSV, no uploadadwarp audience from-salesforce -n <name> -q "<SOQL>"   # Salesforce query -> matched audienceadwarp audience from-hubspot -n <name> --list <id> [--dry-run]   # HubSpot list -> matched audienceadwarp audience from-hubspot -n <name> --filter <prop>:<op>:<value> [-t company]   # HubSpot search -> matched audienceadwarp audience status <segmentId>        # matching status + resolved sizeadwarp conversions list                   # account conversions (pick one to track)adwarp campaigns list [--group <id>] [--all]   # campaign groups + ad groups, drafts includedadwarp ad list <campaignId>               # ads in an ad group (id, status, name), drafts includedadwarp ad delete <creativeId>             # delete an ad (creative + its DSC post)adwarp ad pause <creativeId> [--apply]    # pause a single ad, previews unless --applyadwarp ad resume <creativeId> [--apply]   # set an ad ACTIVE again (starts spend), previews unless --applyadwarp ad archive <creativeId> [--apply]  # archive an ad, previews unless --applyadwarp report summary [-p <period>]       # account rollup: totals, top performers, flagsadwarp report perf <level> [--parent <id>] # per-entity KPI rowsadwarp report trend <level> <id> [-b weekly|monthly]  # trend with deltasadwarp launch --brief <brief.json>        # audience + group + campaign + draft creativesadwarp competitor ads <advertiser>        # any company's ads from the public Ad Library                                        #   <advertiser> = name, company id, or company URL                                        #   -k <keyword> -c <countries> -e auto|api -m <max> --json                                        #   --company-id <id> --copy-max <n> (remote sample, max 10)adwarp changelog list [-t <type>] [-i <id>]           # recorded ad changes, newest firstadwarp changelog add -t <type> -i <id> -f <field> --after <v> [-l <label>]   # log a change made elsewhereadwarp lift <level> <id> [-w <days>]      # before-vs-after performance for each recorded change

Periods: last_7_days, last_30_days, last_90_days, month_to_date, last_month.

--account defaults to defaultAccountId from config where applicable.

Change journal & lift

Adwarp keeps an append-only journal of every change made to an ad entity so you can measure the lift of a change: how performance differed in the window before it versus after.

• Where it lives: ~/.adwarp/changelog.jsonl (one JSON object per line). A plain local file with nothing to set up. Override the path with ADWARP_CHANGELOG_PATH.
• Auto-capture: every create/update Adwarp makes to a campaign group, campaign, or creative is journaled automatically (captured at the one HTTP chokepoint, so it can't be forgotten).
• Manual entries: log changes made outside Adwarp (e.g. in Campaign Manager), or attach a hypothesis, with adwarp changelog add / the log_ad_change tool. Use -l/--label to name the test (e.g. "outcome-led headline test") and --tags to group related changes.
• Lift: adwarp lift <level> <entityId> (or compute_lift) reads the journal for that entity and, for each change, compares the --window days before (default 14) against the same window after, reporting before/after KPIs and per-metric deltas (CTR, CPC, conversion rate, cost-per-conversion, …). Recent changes get a clamped, partial after-window.

This is a directional pre/post comparison, not a controlled experiment. It is confounded by seasonality, the LinkedIn learning phase after an edit, and any concurrent budget change, so treat the deltas as a signal. Set ADWARP_NO_CHANGELOG=1 to disable auto-capture; journaling is also off on hosted deploys (read-only filesystem).

Configuration

Local config lives in ~/.adwarp/config.json (mode 0600, never in the repo):

Hosted equivalents are the ADWARP_LINKEDIN_* env vars plus MCP_AUTH_TOKEN (see Configuration). OAuth tokens are stored separately in ~/.adwarp/credentials.json. A HubSpot private app token, for HubSpot audiences, goes in ~/.adwarp/hubspot.json (mode 0600) or ADWARP_HUBSPOT_TOKEN.

Coming from Liam? Every name from before the rename still works: the ~/.liads folder, the LIADS_* and GADS_* variables, and the X-Liads-* headers. See Names from before the rename.

Salesforce integration

Adwarp reads Salesforce by shelling out to the authenticated sf CLI (sf data query), so it reuses your existing login and needs no new credentials. audience_from_salesforce (and adwarp audience from-salesforce) take a SOQL query that selects an email column and turn the result into a matched audience, closing the loop from "accounts flagged in Salesforce" to "LinkedIn targeting." Example:

adwarp audience from-salesforce -n "Q3 target accounts" \  -q "SELECT Email FROM Contact WHERE Account.Target_List__c = true AND Email != null"

HubSpot integration

Adwarp reads HubSpot with a private app access token you create in your own HubSpot account, with 3 read-only scopes: crm.objects.contacts.read, crm.objects.companies.read and crm.lists.read. Put the token in ~/.adwarp/hubspot.json as { "accessToken": "..." } (mode 0600) or in ADWARP_HUBSPOT_TOKEN. audience_from_hubspot (and adwarp audience from-hubspot) take a HubSpot list id or CRM search filters, read every page, and turn the contacts or companies into a matched audience through the same cleaning and hashing as a CSV upload, so only email hashes leave your machine. It runs locally only. Example:

adwarp audience from-hubspot -n "Q3 target accounts" --list 123 --dry-runadwarp audience from-hubspot -n "Marketing qualified leads" --filter lifecyclestage:EQ:marketingqualifiedlead

See HubSpot audiences for creating the private app and the limits.

Safety

• Every campaign/creative is created DRAFT/PAUSED. Activation is a separate, explicit step.
• Matched-audience matching takes up to 48h, and a campaign needs ~300 matched members to serve.
• LinkedIn does not expose person-level ad-view data; cross-referencing is account/segment-level.
• Secrets never enter the repo. Local: ~/.adwarp. Hosted: Vercel env vars.

Docs

The docs are at adwarp.dev/docs: Install, Create a LinkedIn app, Hosted endpoint, Tools, Skills, CLI, Change journal, Safety and Configuration.

Their source is docs/ in this repo, as plain Markdown, 1 file per topic, each with title, description, and order front matter. The website reads those files from main, so edit them when behavior changes. Links between doc files stay relative (./install.md), and the website turns them into its own page links.

docs/tools.json lists every MCP tool with its description, input schema, platform (linkedin or google), and whether it works on the hosted endpoint (hosted, hostedSupport and hostedNote). It is generated from the real tool registration code, so never edit it by hand. After adding, removing, or changing a tool (including its zod input schema), run:

pnpm gen:tools   # builds @adwarp/mcp and its dependencies, then rewrites docs/tools.json

and commit the result. CI runs the same command and fails if docs/tools.json changes.

License

MIT