MCP server that gives coding agents typed 0xArchive market data tools across Hyperliquid (perps, HIP-3, HIP-4, spot) and Lighter.xyz
Free
Nothing to run from here
Frontrun is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
Frontrun MCP Server - VC follow signal intelligence, company research, and deal discovery for AI agents. 35 tools.
Quickstart
# 1 — run it from where its publisher ships it
npx -y frontrun-mcp-server
# 2 — ask your agent something
> Frontrun MCP Server - VC follow signal intelligence, company research, and deal discovery for AI agents. 35 tools.
Frontrun is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
JOAll 1 server
jongall451 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Frontrun as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add frontrun-mcp -- npx -y frontrun-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it asks of you
Nothing is required, but it can take FRONTRUN_API_KEY if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
33 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Get account status: credit balance, tracked account count, usage stats, and pricing.
Takes no parameters.
Example callreturns →
List all accounts currently being monitored for follow activity.
Takes no parameters.
Example callreturns →
Start monitoring a Twitter/X account for follow activity. 4 credits/account.
Takes no parameters.
Example callreturns →
Stop monitoring a Twitter/X account.
Takes no parameters.
Example callreturns →
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.
Takes no parameters.
Example callreturns →
Detect new follows across tracked accounts. Returns temporal diffs — who each tracked account recently followed and when. 16 credits.
Takes no parameters.
Example callreturns →
Get the current follow list for a tracked account. Shows everyone they currently follow based on stored data. 4 credits.
Takes no parameters.
Example callreturns →
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
Takes no parameters.
Example callreturns →
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.
Takes no parameters.
Example callreturns →
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).
Takes no parameters.
Example callreturns →
Search discovered entities by sector, keyword, or entity type across your tracked universe. 4 credits.
Takes no parameters.
Example callreturns →
Semantic thesis search over your database (companies surfaced by the investors you track). Describe an investment thesis in plain language (e.g.
Takes no parameters.
Example callreturns →
Run AI classification on specific entities. Returns sector, entity type, confidence. 16 credits/entity.
Takes no parameters.
Example callreturns →
Create a custom classification rule. Rules auto-tag entities matching your conditions in enriched follows and discover results. Free.
Takes no parameters.
Example callreturns →
List your custom classification rules. Free.
Takes no parameters.
Example callreturns →
Update an existing custom classification rule. Free.
Takes no parameters.
Example callreturns →
Delete a custom classification rule. Free.
Takes no parameters.
Example callreturns →
Add custom tags, sector override, or notes to a specific entity. Free.
Takes no parameters.
Example callreturns →
List your custom-tagged entities. Free.
Takes no parameters.
Example callreturns →
Synthesized company overview: what they do, sector, stage, website summary, recent activity. Combines Twitter profile, website scrape, and AI classification. 60 credits.
Takes no parameters.
Example callreturns →
Founder intelligence: identifies founders via social graph analysis and enriches with LinkedIn data. Returns name, role, background, previous companies. 100 credits.
Takes no parameters.
Example callreturns →
Social signal analysis: buzz score, sentiment, notable mentions, and which of your tracked VCs follow this entity. 16 credits.
Takes no parameters.
Example callreturns →
Discovered links and resources: website, GitHub, docs, Discord, Telegram. Extracted from profile and website scrape. 60 credits.
Takes no parameters.
Example callreturns →
Funding/deal info cross-referenced with VC follow signals. Returns round details, investors, and which of your tracked VCs follow them. 60 credits.
Takes no parameters.
Example callreturns →
VC follow pattern analysis: velocity, sector distribution, recent follows with classification. 24 credits.
Takes no parameters.
Example callreturns →
Find VCs with similar follow patterns. Computed from temporal follow graph overlap — not raw follower lists. Use this to discover related investors. 60 credits.
Takes no parameters.
Example callreturns →
Real-time activity feed across tracked accounts.
Takes no parameters.
Example callreturns →
Sector breakdown of all discovered entities across your tracked accounts. Shows distribution with counts and percentages. 4 credits.
Takes no parameters.
Example callreturns →
Personalized account recommendations based on your tracked set and custom classification rules.
Takes no parameters.
Example callreturns →
Historical daily reports — the companies discovered in your daily email reports. Filter by date range and sector.
Takes no parameters.
Example callreturns →
List your registered webhooks with status and last delivery time. Free.
Takes no parameters.
Example callreturns →
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.
Takes no parameters.
Example callreturns →
Delete a registered webhook. Free.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Frontrun costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
BTrust score 83 / 100
Release 2.7.0 · scanned 25 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score94
Client score83
Findings2 threat · 1 capability
Capabilitycritical
Coveragesource
Verificationrepo
Surface digest571885eb1cff1d41929e81cbbb6c84673911447348b3f5e340018b9fe01e5b87
Score vectorthreat 94 → client 83
| Term | Level | What it prices | Points |
|---|---|---|---|
| −6.3 | |||
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (36 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| trending_teaser | no tags | |
| send_feedback | no tags | |
| frontrun_status | no tags | |
| frontrun_list_tracked | no tags | |
| frontrun_track | no tags | |
| frontrun_untrack | no tags | |
| frontrun_preview | no tags | |
| frontrun_new_follows | no tags | |
| frontrun_snapshot | no tags | |
| frontrun_enriched_follows | no tags | |
| frontrun_convergence | no tags | |
| frontrun_trending | no tags | |
| frontrun_search | no tags | |
| frontrun_thesis_search | no tags | |
| frontrun_classify | no tags | |
| frontrun_create_rule | no tags | |
| frontrun_list_rules | no tags | |
| frontrun_update_rule | no tags | |
| frontrun_delete_rule | no tags | |
| frontrun_tag | no tags | |
| frontrun_list_tags | no tags | |
| frontrun_company | no tags | |
| frontrun_company_founders | no tags | |
| frontrun_founders_batch | no tags | |
| frontrun_company_signals | no tags | |
| frontrun_company_resources | untrusted-input | |
| frontrun_company_funding | no tags | |
| frontrun_vc_activity | no tags | |
| frontrun_vc_similar | no tags | |
| frontrun_feed | no tags | |
| frontrun_sectors | no tags | |
| frontrun_discover | no tags | |
| frontrun_reports | no tags | |
| frontrun_list_webhooks | no tags | |
| frontrun_create_webhook | external-sink | |
| frontrun_delete_webhook | external-sink |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest571885eb1cff1d41
Scanned2026-08-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 2.7.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
2.7.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Frontrun in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.