# Sellinger CRM (npm · sellinger-mcp)

Manage Sellinger AI SDR CRM leads, conversations and pipeline from any MCP client.

- Trust score: 62/100 (medium)
- Change this week: +29
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- npm · `sellinger-mcp`: 62/100 (this document), [markdown](https://verifymcp.io/servers/ai-sellinger-mcp-server/sellinger-mcp.md), [page](https://verifymcp.io/servers/ai-sellinger-mcp-server/sellinger-mcp)

## Channel facts

- Registry: `npm`
- Package: `sellinger-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1248 tokens (~83/item across 15 items; 15 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Sellinger CRM MCP server?

Sellinger CRM runs locally as an npm package, launched with npx -y sellinger-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add ai-sellinger-mcp-server -- npx -y sellinger-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ai-sellinger-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "sellinger-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-sellinger-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "sellinger-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-sellinger-mcp-server -- npx -y sellinger-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-sellinger-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "sellinger-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-sellinger-mcp-server --command npx --arg -y --arg sellinger-mcp
```

### Hermes

```yaml
mcp_servers:
  ai-sellinger-mcp-server:
    command: "npx"
    args: ["-y", "sellinger-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-sellinger-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "sellinger-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-sellinger-mcp-server -t stdio -c npx -a -y sellinger-mcp
```

### Other

```json
{
  "mcpServers": {
    "ai-sellinger-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "sellinger-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-14 (score 62, +29)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 0
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 86

### 2026-10-12 (score 33, 0)

- [security improvement] Malware scan: unverified → pass

### 2026-10-11 (score 33, +15)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-10-07 (score 18)

First indexed and scored.

## MCP tools (15)

### `list_leads` (~130 tokens)

List leads from the CRM with optional filters. Returns a paginated array of leads.

Input parameters:

- `page` (number): Page number (1-based). Defaults to 1.
- `per_page` (number): Number of results per page (max 100). Defaults to 25.
- `search` (string): Search query to filter leads by name, company, or email
- `stage` (string): Filter by pipeline stage name or ID
- `status` (string): Filter by lead status (e.g. "NEW", "ENGAGED", "CONVERTED", "IRRELEVANT")

### `get_lead` (~40 tokens)

Retrieve a single lead by its UUID. Returns the full lead record with all fields.

Input parameters:

- `id` (string, required): The UUID of the lead to retrieve

### `create_lead` (~147 tokens)

Create a new lead in the CRM. Returns the newly created lead record.

Input parameters:

- `company` (string): Lead's company or organization
- `email` (string): Lead's email address
- `first_name` (string, required): Lead's first name
- `last_name` (string, required): Lead's last name
- `linkedin_url` (string): URL to the lead's LinkedIn profile
- `notes` (string): Free-form notes about the lead
- `phone` (string): Lead's phone number
- `source` (string): How the lead was acquired (e.g. "mcp", "manual", "linkedin")
- `title` (string): Lead's job title

### `update_lead` (~394 tokens)

Update fields on an existing lead. Only provided fields will be changed. Do NOT update the updated_at field. To RELEASE a lead a human took over, send human_takeover=false. To record that the person asked us to stop, prefer the opt_out tool/endpoint over setting takeover_source here — a takeover_source label is per-lead and anyone can overwrite it, whereas an opt-out must also be recorded person-level.

Input parameters:

- `company` (string): Updated company
- `email` (string): Updated email
- `full_name` (string): Updated full name
- `human_takeover` (boolean): Whether a human owns this conversation. true fences the lead from ALL automated outbound; false RELEASES it back to the agent. This is a mute as well as a consent fence.
- `id` (string, required): UUID of the lead to update
- `notes` (string): Updated notes
- `phone` (string): Updated phone
- `pipeline_stage` (string): Name of the pipeline stage to move the lead to (not a UUID)
- `status` (string): New status (e.g. "NEW", "ENGAGED", "CONVERTED")
- `takeover_source` (string|null): WHO raised the fence that is currently in effect: 'user' (someone on your side), 'worker' (this product's automation), 'opt_out' (the person asked us to stop). This is a LABEL and gates nothing here…
- `title` (string): Updated job title

### `opt_out_lead` (~133 tokens)

Record that a person asked us to stop contacting them. This is the SUPPORTED way to honour an opt-out: it writes a person-level do-not-contact record for every identifier on the lead (email, phone, LinkedIn) AND fences the lead, in one transaction. Prefer this over update_lead(takeover_source='opt_out'), which only labels one lead row and gates nothing.

Input parameters:

- `id` (string, required): UUID of the lead who asked us to stop
- `reason` (string): Optional short note for the record, e.g. the words they used. Defaults to 'unsubscribed'.

### `send_message` (~74 tokens)

Send a message to a lead via a specified channel (email, linkedin, whatsapp).

Input parameters:

- `body` (string, required): Message body / content
- `channel` (string, required): Communication channel to use
- `lead_id` (string, required): UUID of the lead to message
- `subject` (string): Message subject (required for email)

### `list_segments` (~40 tokens)

List all segments (saved lead filters/groups) in the CRM.

Input parameters:

- `include_counts` (boolean): Whether to include lead counts per segment. Defaults to false.

### `get_analytics` (~44 tokens)

Retrieve a KPI summary including total leads, conversion rate, response rate, and pipeline distribution.

Input parameters:

- `period` (string): Time period for analytics. Defaults to "30d".

### `search_leads` (~74 tokens)

Full-text search across all lead fields. More powerful than list_leads search parameter.

Input parameters:

- `limit` (number): Maximum number of results to return (max 50). Defaults to 10.
- `query` (string, required): Search query. Matches against name, company, email, title, notes, and other text fields.

### `list_agents` (~17 tokens)

List all Sellinger agents for the team.

### `get_agent` (~28 tokens)

Get a single agent by UUID including configs and channels.

Input parameters:

- `id` (string, required): Agent UUID

### `list_approvals` (~56 tokens)

List pending approvals (messages, actions, suggestions).

Input parameters:

- `agent_id` (string)
- `channel` (string)
- `limit` (number)
- `status` (string): Filter by status (default: pending)

### `get_pipeline_counts` (~16 tokens)

Get lead counts per pipeline stage.

### `list_companies` (~36 tokens)

List companies in the CRM.

Input parameters:

- `limit` (number)
- `offset` (number)
- `search` (string)

### `get_hot_leads` (~19 tokens)

Get high-intent leads from intent signals.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-sellinger-mcp-server/sellinger-mcp#diagnostics

## Score history

- 2026-10-18: 62
- 2026-10-17: 62
- 2026-10-16: 62
- 2026-10-15: 62
- 2026-10-14: 62
- 2026-10-13: 33
- 2026-10-12: 33
- 2026-10-11: 33
- 2026-10-07: 18

## Common questions

### What is the Sellinger CRM MCP server?

Sellinger CRM is an MCP server listed in the public MCP registry as ai.sellinger/mcp-server. Manage Sellinger AI SDR CRM leads, conversations and pipeline from any MCP client. This page covers its npm package (sellinger-mcp).

### Is the Sellinger CRM MCP server safe to use?

Sellinger CRM scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Sellinger CRM MCP server expose?

Sellinger CRM exposes 15 tools: list_leads, get_lead, create_lead, update_lead, opt_out_lead, and 10 more. Their descriptions and schemas cost roughly 1,248 tokens of context every time the server is loaded.

### Is the Sellinger CRM MCP server still maintained?

Sellinger CRM is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Sellinger CRM MCP server under?

Sellinger CRM declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/sellinger-mcp
- Socket report: https://socket.dev/npm/package/sellinger-mcp
- Website: https://sellinger.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-sellinger-mcp-server/sellinger-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-sellinger-mcp-server/sellinger-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-sellinger-mcp-server/sellinger-mcp