ToolTrust
C40/100
Smithery

pipelinescientists-coldsend-mcp

mcpsmithery

@Smithery

AI-native cold email campaign management via Model Context Protocol. ## What You Can Do - **Campaigns** — Create, launch, pause, resume, and delete email campaigns with full lifecycle control - **Leads** — Upload leads from CSV, list, filter, and manage recipients per campaign - **Sender Accounts** — Configure ColdSend native, SMTP, Google Workspace, and Outlook 365 inboxes - **Domains** — Add custom sending domains with automated DNS verification and activation tracking - **Analytics** — Track delivery rates, open/click engagement, reply rates, and compare campaigns side-by-side - **Inbox Health** — Monitor sender reputation, bounce rates, and deliverability scores ## Authentication Pass your ColdSend API key via the `X-API-Key` header. Get your key from [cloud.coldsend.pro](https://cloud.coldsend.pro). ## Transports - Streamable HTTP (`/mcp`)

By Smithery | 50 findings | Scanned 4/19/2026 | tooltrust-scanner/v0.3.8

2 High9 Medium9 Low30 Info

Risk Summary

Needs Approval

Dep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (50)

  • HighAS-002

    ⚠️Excessive Permissions

    sender.create_smtp:tool declares network permission

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • HighAS-010

    🔑Insecure Secret Handling

    sender.create_smtp:input parameter "smtp_password" appears to accept a secret or credential

    Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.

  • MediumAS-002

    ⚠️Excessive Permissions ×9

    tool declares fs permission

    campaigns.createcampaigns.deleteleads.uploadleads.deletedomains.deletesender.create_coldsendsender.create_smtpsender.deletecampaigns.update

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • LowAS-002

    ⚠️Excessive Permissions ×4

    tool declares http permission

    campaigns.resumesender.testsender.resumecampaigns.activate

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×5

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    campaigns.resumesender.create_smtpsender.testsender.resumecampaigns.activate

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×30

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    campaigns.createcampaigns.listcampaigns.getcampaigns.pausecampaigns.resumecampaigns.deleteleads.uploadleads.listleads.deleteleads.statsanalytics.campaignanalytics.accountanalytics.inboxanalytics.comparedomains.listdomains.getdomains.adddomains.verifydomains.progressdomains.deletesender.listsender.create_coldsendsender.create_smtpsender.testsender.pausesender.resumesender.deletesender.healthcampaigns.updatecampaigns.activate

    Fix: Review and remediate the identified issue.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y pipelinescientists-coldsend-mcp"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)