ToolTrust
A2/100
Smithery

hello-lc0b-earlywire

mcpsmithery

@Smithery

** Earlywire — Marketing & Growth Intelligence is the marketing & growth wire for AI assistants. It reads 120+ curated practitioner sources every morning — newsletters, vendor changelogs, and the SEO, analytics and paid-media feeds that matter — and scores each piece 0–10 for signal (only score ≥7 is served). Your assistant gets fresh, judged items with a citable own-words summary and a link to the source, instead of whatever ranks on web search. Use it alongside web search, not instead of it. **Connect (Claude Code):** `claude mcp add --transport http earlywire https://earlywire.barisasa.com/mcp` **Add the skill (so it actually fires):** The skill tells Claude to consult Earlywire — alongside web search — for marketing questions, so it gets used instead of defaulting to the open web. `/plugin marketplace add barisasaa/earlywire then /plugin install earlywire-marketing` (installs the skill and the connector in one step). claude.ai / Desktop: full two-step setup at https://earlywire.barisasa.com/setup Free, no key, 30 requests/minute. **Tools** - `earlywire_search` — full-text search across the corpus - `earlywire_topic_pulse` — what the niche is saying: volume, sources, score spread, top takes - `earlywire_whats_new` — newest judged items, by category - `earlywire_trending` — topics rising vs the prior window - `earlywire_get_item` — one item's summary + excerpt + source link - `earlywire_coverage` — sources, freshness, category mix Own-words summary + short excerpt, always linked to source. Covers marketing, growth, analytics, paid media, SEO and AI search — plus the AI shifts reshaping them.

By Smithery | 10 findings | Scanned 7/26/2026 | tooltrust-scanner/v0.3.19

2 Low8 Info

Risk Summary

Safe With Normal Controls

Dep Visibility is the main signal, but overall risk remains within an acceptable range.

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

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

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

Security Findings (10)

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×2

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

    searchget_item

    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 ×6

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

    whats_newsearchtopic_pulsetrendingget_itemcoverage

    Fix: Review and remediate the identified issue.

  • InfoAS-002

    ⚠️Excessive Permissions ×2

    declared capabilities: network access, database access

    search

    declared capabilities: network access

    get_item

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

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 hello-lc0b-earlywire"

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 A](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-a.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)