Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-clay-to-instantly-smartlead-push Dry run: push leads from dataset abc123 to Instantly campaign 456"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for the Mamba Labs Sequencer Lead Push actor on Apify.
Push enriched lead rows into an existing Instantly or Smartlead campaign. ICP score gating and deduplication are built in, and a dry run shows you the exact payload before you send anything.
npx -y @mambalabsdev/mcp-clay-to-instantly-smartlead-push{
"mcpServers": {
"mamba-clay-to-instantly-smartlead-push": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-clay-to-instantly-smartlead-push"],
"env": { "APIFY_TOKEN": "your-apify-token" }
}
}
}Get an Apify token at console.apify.com/account/integrations.
Related MCP server: Instantly MCP Server
push_leads_to_sequencerMaps your column names onto the sequencer's field names, drops leads below your ICP score threshold, drops leads already in the campaign, and sends the rest in batches.
Input | Type | Required | Notes |
| string | yes |
|
| string | yes | The target campaign. It must already exist. |
| string | see note | Your Instantly v2 key or Smartlead key |
| array | one of | Lead rows. Each needs an |
| string | one of | An Apify dataset ID from an upstream run |
| number | no | Drop leads scoring below this. Default 0. |
| boolean | no | Check the campaign first. Default true. |
| boolean | no | Preview without sending. Default false. |
| object | no | Override the default column map |
| array | no | Extra columns to pass through |
api_key is required for any run that calls the sequencer. A dry run with deduplicate false makes no calls at all and needs no key.
Returns one flat summary row: leads received, dropped for no usable identity (an email, or a LinkedIn profile URL on HeyReach), dropped by the ICP gate, dropped as duplicates, eligible, created by the sequencer, skipped by the sequencer, and failed, with the vendor's own message per failed address.
dry_run: true runs every step, returns the exact request batches that would have been sent, and creates nothing. Nothing is billed.
Use it the first time you point at a new campaign. The payload you see is the real one, and your API key is never included in it.
You are charged per lead the sequencer confirms it created. Leads dropped by the gate, dropped as duplicates, with no usable email, skipped or rejected by the vendor, and every lead in a dry run are all free.
Pricing is on the actor's Apify page. Running this server consumes Apify credits.
Sequencer | API | Notes |
Instantly | v2 | Needs a v2 key. Keys from v1 do not work: Instantly deprecated v1 on January 19, 2026. |
Smartlead | v1 | Current. Smartlead has no v2. |
It is a thin client for the Apify actor. It passes your input through and returns the actor's output. The field mapping, the ICP gate, the deduplication and everything either vendor's API needs all live in the actor, not here.
It writes to your sequencer campaign unless dry_run is true. It does not create campaigns and it does not write sequence copy.
Part of the Mamba Labs GTM actor fleet. The same tool is available alongside fourteen others in @mambalabsdev/mcp-gtm-suite.
Built by Mamba Labs
Push enriched lead rows into an existing Instantly or Smartlead campaign. Maps common Clay column names onto each sequencer's own field names, optionally drops leads below a minimum ICP score, optionally deduplicates against the leads already in the destination campaign, and sends the rest in batches. Returns one flat summary row: how many leads were received, dropped for having no usable email, dropped by the ICP gate, dropped as duplicates, eligible, actually created by the sequencer, skipped by the sequencer, and failed, plus the vendor's own error message per failed address. The campaign must already exist; this does not create campaigns or write sequence copy. Set dry_run true to get back the exact request payload that would be sent without creating a single lead and without being charged, which is the safe way to check a mapping against a new campaign. Billing is per lead the sequencer confirms it created, so gated, duplicate, skipped, failed and dry-run leads are all free. Instantly uses API v2 and needs a v2 key; Smartlead uses API v1. Requires an APIFY_TOKEN and consumes Apify credits. This WRITES to your sequencer campaign unless dry_run is true.
| Name | Required | Description | Default |
|---|---|---|---|
| leads | No | Lead rows to push. Each row needs an email at minimum. Takes precedence over dataset_id when both are set. | |
| api_key | No | Your Instantly v2 API key or your Smartlead API key. An Instantly v1 key will not work: v1 was deprecated on January 19, 2026. Required for any run that calls the sequencer. A dry run with deduplicate false makes no calls and needs no key. | |
| dry_run | No | Run every step, return the exact payload that would be sent, and make zero write calls. Creates no leads and charges nothing. Default false. | |
| sequencer | Yes | Which sequencer to push to. Instantly uses API v2, Smartlead uses API v1. | |
| dataset_id | No | An Apify dataset ID from an upstream run, for example the output of the ICP Fit Scorer. Used only when leads is empty. | |
| campaign_id | Yes | The target campaign in the sequencer. It must already exist. Instantly campaign IDs are UUIDs; Smartlead campaign IDs are numeric. | |
| deduplicate | No | Read the campaign's existing leads first and drop any email already there. Default true. This is a read, so it needs an API key even on a dry run. | |
| field_mapping | No | Override the default Clay column to sequencer field map. Keys are your column names, values are the sequencer field names. Set a value to an empty string to drop that column. A target the sequencer does not have is sent as a custom variable rather than rejected. | |
| min_icp_score | No | Drop leads whose icp_score is below this number. Default 0, which pushes everything. Rows with no icp_score are always kept. | |
| custom_variables | No | Extra column names to pass through as custom variables under their own name. Columns that are neither mapped nor listed here are dropped. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explicitly discloses write behavior: 'This WRITES to your sequencer campaign unless dry_run is true,' which aligns with readOnlyHint=false. It goes beyond annotations by explaining billing (per lead confirmed created), API key requirements (Instantly v2, Smartlead v1), and dry-run semantics (zero write calls, no charge). This is rich behavioral context with no contradiction to the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a dense paragraph of about seven sentences, each covering a distinct aspect: purpose, core behavior, return payload, constraints, dry-run, billing, and API specifics. It is logically structured and front-loaded with the main action; while longer than minimal examples, every sentence earns its place for a tool with 10 parameters and no output schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description compensates thoroughly by specifying the exact return shape: 'one flat summary row: how many leads were received, dropped... plus the vendor's own error message.' It also covers prerequisites, side effects, billing, and API nuances, making it complete for a complex write tool with 10 parameters and a nested input schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Even with 100% schema coverage, the description adds significant meaning: it explains parameter precedence ('leads... takes precedence over dataset_id'), the deduplicate API-key requirement on dry runs, and the ICP gate default ('Rows with no icp_score are always kept'). It also clarifies how field_mapping treats unknown targets and how custom_variables pass through, which the schema alone does not convey.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Push enriched lead rows into an existing Instantly or Smartlead campaign.' It further details the tool's scope (field mapping, ICP filtering, deduplication, batching) and its flat summary return. Although no sibling tools are listed, the purpose is unambiguous and self-contained.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives concrete usage guidance and prerequisites: 'The campaign must already exist; this does not create campaigns or write sequence copy,' and 'Set dry_run true to get back the exact request payload... the safe way to check a mapping against a new campaign.' It also notes when an API key is needed even on dry_run (deduplicate) and contrasts API versions for Instantly vs Smartlead. It does not list alternative tools, but the provided context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0push_leads_to_sequencerOnly a single tool exists, so there is no possibility of overlapping purposes. The tool's description clarifies it handles both Instantly and Smartlead pushes, but that's a single atomic operation.
The single tool name follows a clear verb_noun pattern (push_leads_to_sequencer), and with only one tool, there is no inconsistency.
At one tool, the server sits at the thin end of the scale. However, the narrow purpose of pushing leads to sequencing vendors justifies a minimal surface, though users may need complementary tools from other servers.
For its stated purpose of pushing enriched leads to existing campaigns, the tool covers all essential features: mapping, filtering, deduplication, dry run, batching, and detailed reporting. It explicitly does not create campaigns, which is outside its scope.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Find scored B2B leads, read campaign replies and send approved LinkedIn outreach.
Build prospecting lists from buying signals, enrich them, and run LinkedIn outreach.
Run B2B outreach from your AI agent: 250+ tools for campaigns, leads, LinkedIn and email workflows.
Find, qualify and message B2B leads from public LinkedIn data; every send is human-approved.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mambalabsdev/mcp-clay-to-instantly-smartlead-push'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
