# io.github.jongall45/frontrun-mcp-server (npm · frontrun-mcp-server)

Track what 1,000+ VCs follow on X to surface startups before their round. Signal for AI agents.

- Trust score: 66/100 (medium)
- Change this week: +40
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `frontrun-mcp-server`: 66/100 (this document), [markdown](https://verifymcp.io/servers/jongall45-frontrun-mcp-server/frontrun-mcp-server.md), [page](https://verifymcp.io/servers/jongall45-frontrun-mcp-server/frontrun-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `frontrun-mcp-server`
- Version: `2.6.0`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 2603 tokens (~74/item across 35 items; 35 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**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **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

### Claude

```bash
claude mcp add jongall45-frontrun-mcp-server -- npx -y frontrun-mcp-server
```

### Codex

```bash
codex mcp add jongall45-frontrun-mcp-server -- npx -y frontrun-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jongall45-frontrun-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "frontrun-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jongall45-frontrun-mcp-server --command npx --arg -y --arg frontrun-mcp-server
```

### Hermes

```yaml
mcp_servers:
  jongall45-frontrun-mcp-server:
    command: "npx"
    args: ["-y", "frontrun-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "jongall45-frontrun-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "frontrun-mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 66, −3)

No change was recorded against any check on this day. Supply Chain Security went from 97 to 87.

### 2026-08-01 (score 69, +49)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 20, −8)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 28, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-28 (score 46, +20)

- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: unverified
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass

### 2026-07-27 (score 26)

First indexed and scored.

## MCP tools (35)

### `trending_teaser` (~86 tokens)

FREE SAMPLE - no auth or API key needed. Top 5 trending companies from Frontrun's follow graph over the last 7 days: name, X handle, sector, follower count, first-flagged date, and how many tracked investors newly followed each (counts only - investor identities require a plan). Use this to try Frontrun before configuring a key.

### `send_feedback` (~147 tokens)

Send feedback to the Frontrun team - no auth or API key needed. Hit a confusing error, a missing capability, or a docs gap? Report it here so we can fix it for agents like you. Include the tool name and your agent runtime if relevant.

Input parameters:

- `agent` (string): Your agent runtime, e.g. "claude-code"
- `contact` (string): Optional contact (email/X handle) if you want a reply
- `message` (string, required): The feedback itself (required, max 2000 chars)
- `tool` (string): Which Frontrun tool/endpoint this is about, e.g. "frontrun_trending"

### `frontrun_status` (~27 tokens)

Get account status: credit balance, tracked account count, usage stats, and pricing.

### `frontrun_list_tracked` (~22 tokens)

List all accounts currently being monitored for follow activity.

### `frontrun_track` (~40 tokens)

Start monitoring a Twitter/X account for follow activity. 4 credits/account.

Input parameters:

- `username` (string, required): Twitter/X handle to track (without @)

### `frontrun_untrack` (~34 tokens)

Stop monitoring a Twitter/X account.

Input parameters:

- `username` (string, required): Twitter/X handle to stop tracking (without @)

### `frontrun_preview` (~66 tokens)

Preview an account before tracking. Returns profile summary, signal potential score (0-1), sector hints, and a tracking recommendation. Use this to evaluate whether an account is worth monitoring. 4 credits.

Input parameters:

- `handle` (string, required): Twitter/X handle to preview (without @)

### `frontrun_new_follows` (~119 tokens)

Detect new follows across tracked accounts. Returns temporal diffs - who each tracked account recently followed and when. 16 credits.

Input parameters:

- `classify` (boolean): Include AI classification for each new follow
- `hours` (number): Shorthand: hours to look back (e.g. 48). Alternative to since.
- `since` (string): Time window: "24h", "7d", "30d", or ISO date. Default: "24h"
- `username` (string): Filter to a specific tracked account

### `frontrun_snapshot` (~48 tokens)

Get the current follow list for a tracked account. Shows everyone they currently follow based on stored data. 4 credits.

Input parameters:

- `username` (string, required): Twitter/X handle of the tracked account

### `frontrun_enriched_follows` (~201 tokens)

New follows with full enrichment: AI classification + custom rules + custom tags + filtering. The most powerful signal endpoint. Use sector/keyword/entity_type filters to query like "show me all stablecoin neobanks my tracked VCs followed this week". 16 credits.

Input parameters:

- `entity_type` (string): Filter by type: "company", "project", "person", "fund", "vc"
- `hours` (number): Shorthand: hours to look back
- `keyword` (string): Search keyword (matches username, name, bio, sector)
- `sector` (string): Filter by sector (e.g. "DeFi", "AI", "stablecoins")
- `since` (string): Time window: "24h", "7d", etc. Default: "24h"
- `tag` (string): Filter by custom tag or rule name
- `username` (string): Filter to a specific tracked account

### `frontrun_convergence` (~110 tokens)

Detect convergence: entities followed by multiple tracked accounts independently. The highest-signal endpoint - when 3+ VCs independently follow the same account, it strongly suggests pre-funding interest. 60 credits.

Input parameters:

- `hours` (number): Shorthand: hours to look back
- `min_accounts` (number): Minimum tracked accounts that must follow. Default: 2. Use 3+ for high-conviction.
- `since` (string): Time window. Default: "7d"

### `frontrun_trending` (~87 tokens)

Entities ranked by follow velocity - how many tracked accounts recently followed them. Use this for daily deal flow. 24 credits (+16 credits per item if classify=true).

Input parameters:

- `classify` (boolean): Include AI classification
- `limit` (number): Max results (max 100). Default: 25
- `since` (string): Time window. Default: "7d"

### `frontrun_search` (~116 tokens)

Search discovered entities by sector, keyword, or entity type across your tracked universe. 4 credits.

Input parameters:

- `entity_type` (string): Filter: "company", "project", "person", "fund", "vc"
- `keyword` (string): Search keyword (matches username, sector, bio)
- `limit` (number): Max results (max 200). Default: 50
- `sector` (string): Filter by sector: "DeFi", "AI", "Infrastructure", "Gaming", "Payments", etc.

### `frontrun_thesis_search` (~109 tokens)

Semantic thesis search over your database (companies surfaced by the investors you track). Describe an investment thesis in plain language (e.g. "information markets - platforms where people trade on what they know") and get companies whose descriptions match the meaning, not just the exact words. Ranked by similarity. 40 credits.

Input parameters:

- `limit` (number): Max results (max 50). Default: 25
- `q` (string, required): Investment thesis in plain language (min 10 characters)

### `frontrun_classify` (~56 tokens)

Run AI classification on specific entities. Returns sector, entity type, confidence. 16 credits/entity.

Input parameters:

- `twitter_user_ids` (array): Twitter user IDs to classify
- `usernames` (array): Usernames to classify

### `frontrun_create_rule` (~84 tokens)

Create a custom classification rule. Rules auto-tag entities matching your conditions in enriched follows and discover results. Free.

Input parameters:

- `actions` (object, required): What to apply when conditions match
- `conditions` (object, required): Conditions that must ALL be met
- `name` (string, required): Rule name, e.g. "DeFi Protocols" or "stablecoin-neobank"

### `frontrun_list_rules` (~19 tokens)

List your custom classification rules. Free.

### `frontrun_update_rule` (~71 tokens)

Update an existing custom classification rule. Free.

Input parameters:

- `actions` (object): Updated actions
- `active` (boolean): Enable or disable the rule
- `conditions` (object): Updated conditions
- `id` (string, required): Rule UUID to update
- `name` (string): New rule name

### `frontrun_delete_rule` (~30 tokens)

Delete a custom classification rule. Free.

Input parameters:

- `id` (string, required): Rule UUID to delete

### `frontrun_tag` (~104 tokens)

Add custom tags, sector override, or notes to a specific entity. Free.

Input parameters:

- `custom_entity_type` (string): Custom entity type override
- `custom_sector` (string): Custom sector override
- `notes` (string): Free-text notes
- `tags` (array): Tags, e.g. ["watchlist", "portfolio"]
- `twitter_user_id` (string): Twitter user ID
- `username` (string): Username (alternative to twitter_user_id)

### `frontrun_list_tags` (~42 tokens)

List your custom-tagged entities. Free.

Input parameters:

- `sector` (string): Filter by custom sector
- `tag` (string): Filter by tag name

### `frontrun_company` (~58 tokens)

Synthesized company overview: what they do, sector, stage, website summary, recent activity. Combines Twitter profile, website scrape, and AI classification. 60 credits.

Input parameters:

- `handle` (string, required): Twitter/X handle (without @)

### `frontrun_company_founders` (~59 tokens)

Founder intelligence: identifies founders via social graph analysis and enriches with LinkedIn data. Returns name, role, background, previous companies. 100 credits.

Input parameters:

- `handle` (string, required): Twitter/X handle of the company (without @)

### `frontrun_company_signals` (~52 tokens)

Social signal analysis: buzz score, sentiment, notable mentions, and which of your tracked VCs follow this entity. 16 credits.

Input parameters:

- `handle` (string, required): Twitter/X handle (without @)

### `frontrun_company_resources` (~53 tokens)

Discovered links and resources: website, GitHub, docs, Discord, Telegram. Extracted from profile and website scrape. 60 credits.

Input parameters:

- `handle` (string, required): Twitter/X handle (without @)

### `frontrun_company_funding` (~57 tokens)

Funding/deal info cross-referenced with VC follow signals. Returns round details, investors, and which of your tracked VCs follow them. 60 credits.

Input parameters:

- `handle` (string, required): Twitter/X handle (without @)

### `frontrun_vc_activity` (~60 tokens)

VC follow pattern analysis: velocity, sector distribution, recent follows with classification. 24 credits.

Input parameters:

- `handle` (string, required): Twitter/X handle of the tracked VC
- `since` (string): Time window. Default: "30d"

### `frontrun_vc_similar` (~99 tokens)

Find VCs with similar follow patterns. Computed from temporal follow graph overlap - not raw follower lists. Use this to discover related investors. 60 credits.

Input parameters:

- `handle` (string, required): Twitter/X handle of the tracked VC
- `limit` (number): Max results (max 50). Default: 20
- `min_overlap` (number): Minimum overlap score (0-1). Default: 0.1

### `frontrun_feed` (~120 tokens)

Real-time activity feed across tracked accounts. "Who has my tracked list followed today?" Filter by event type (new_follow, convergence) and sector. 16 credits.

Input parameters:

- `event_type` (string): Filter: "new_follow" or "convergence"
- `hours` (number): Shorthand: hours to look back
- `limit` (number): Max events (max 200). Default: 50
- `sector` (string): Filter targets by sector
- `since` (string): Time window. Default: "24h"

### `frontrun_sectors` (~33 tokens)

Sector breakdown of all discovered entities across your tracked accounts. Shows distribution with counts and percentages. 4 credits.

### `frontrun_discover` (~97 tokens)

Personalized account recommendations based on your tracked set and custom classification rules. "You track 50 VCs - here are accounts they follow that you're not tracking yet." 60 credits.

Input parameters:

- `limit` (number): Max results (max 50). Default: 20
- `min_signal` (number): Minimum signal score (0-1). Default: 0.3
- `sector` (string): Narrow by sector

### `frontrun_reports` (~135 tokens)

Historical daily reports - the companies discovered in your daily email reports. Filter by date range and sector. "Show me last week's stablecoin discoveries." 4 credits.

Input parameters:

- `date` (string): Specific date: "YYYY-MM-DD"
- `limit` (number): Max reports to return (max 30). Default: 7
- `sector` (string): Filter by sector keyword (e.g. "stablecoin", "DeFi", "AI")
- `since` (string): Time range: "7d", "14d", "30d", or "YYYY-MM-DD". Default: "7d"

### `frontrun_list_webhooks` (~26 tokens)

List your registered webhooks with status and last delivery time. Free.

### `frontrun_create_webhook` (~105 tokens)

Register a webhook to receive push notifications for signal events (new_follows, convergence). Deliveries are signed with your secret if provided. 40 credits setup + 8 credits per delivery.

Input parameters:

- `events` (array, required): Event types to subscribe to
- `filters` (object): Optional event filters (AND logic)
- `secret` (string): Secret used to HMAC-sign delivery payloads
- `url` (string, required): HTTPS endpoint to receive event payloads

### `frontrun_delete_webhook` (~31 tokens)

Delete a registered webhook. Free.

Input parameters:

- `id` (string, required): Webhook ID to delete

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/jongall45-frontrun-mcp-server/frontrun-mcp-server#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 66
- 2026-08-01: 69
- 2026-07-31: 20
- 2026-07-30: 28
- 2026-07-28: 46
- 2026-07-27: 26

## Links

- npm package: https://www.npmjs.com/package/frontrun-mcp-server
- Socket report: https://socket.dev/npm/package/frontrun-mcp-server
- Repository: https://github.com/jongall45/frontrun-mcp-server
- Website: https://www.frontrun.vc/
- Changelog RSS feed: https://verifymcp.io/servers/jongall45-frontrun-mcp-server/frontrun-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/jongall45-frontrun-mcp-server/frontrun-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/jongall45-frontrun-mcp-server/frontrun-mcp-server