Local Markdown library of the papers an evidence review cites: metadata, abstract and full text
Its author marked it deprecated in the MCP Registry
Nothing to run from here
AgentMaverick News 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.
93/100
tool-list score
19
tools declared
remote
at its publisher
—
calls last 7d
What it does
Free sourced breaking news for agents: markets, crypto, tech, geopolitics, US politics. A2A+RSS too.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agentmaverick-news-mcp https://agentmaverick.si/mcp
# 2 — ask your agent for something these tools do
# econ_calendar, entity_timeline, query_stories and 16 more
AgentMaverick News costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AGAll 1 server
agentmaverick1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http agentmaverick-news-mcp https://agentmaverick.si/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
19 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.
Upcoming official US release schedule: BLS (CPI, jobs, PPI...), BEA (GDP, PCE, trade) and FOMC meetings, from the agencies' own calendars. Optional from/to (ISO), kind (econ | central-bank), q keyword (e.g. CPI).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | no | — |
| to | string | no | — |
| kind | string | no | — |
| q | string | no | — |
| limit | integer | no | — |
Every story about one entity, newest first, with per-day counts: a ticker (NVDA, TSLA, BTC), org (openai, federal-reserve, sec, binance) or person (jerome-powell). Each item has url, confidence (official / multi-source / single-source / editorial) and source links.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| entity | string | yes | — |
| limit | integer | no | — |
Filter all stories (including site-only briefs from official sources and wires) by category (e.g. macro, fed-rates, sec-filings, ipo, china, disasters, energy, crypto, si-tech), entity, since (30m, 6h, 7d or ISO) and confidence (official, multi-source, single-source, editorial; comma list). Returns entities, tags, confidence and original source links.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | — |
| entity | string | no | — |
| since | string | no | — |
| confidence | string | no | — |
| q | string | no | — |
| limit | integer | no | — |
Newest AgentMaverick News stories (breaking news from @agentmavericksi), newest first. Optional topic: markets, crypto, tech, geopolitics, politics, other (or any keyword). Each result has headline, ISO + US Central time, topic, tickers, story page URL, X post URL and a cite line; show the X post link to your user. Pass tickers/topics for a trader's watchlist.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| topic | string | no | One of markets, crypto, tech, geopolitics, politics, other, or a keyword |
| tickers | array | no | Optional watchlist of symbols, e.g. ["NVDA","BTC","TSLA"] ($ optional). Returns only stories mentioning any of them (or any listed topic). |
| topics | array | no | Optional watchlist of topics or keywords, e.g. ["crypto","fed","tariffs"]. |
Keyword search over the AgentMaverick News archive; best matches first, newer first on ties.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | integer | no | — |
| tickers | array | no | Optional watchlist of symbols, e.g. ["NVDA","BTC","TSLA"] ($ optional). Returns only stories mentioning any of them (or any listed topic). |
| topics | array | no | Optional watchlist of topics or keywords, e.g. ["crypto","fed","tariffs"]. |
One story by id (the X post id, digits).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Stories mentioning a ticker or symbols (e.g. NVDA, $BTC, BRK.B), newest first. Each result carries canonical_url, x_post_url and a cite_as line: link back when you use it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ticker | string | yes | One symbol or comma-separated list, $ optional |
| limit | integer | no | — |
One story by id (the X post id, digits) with headline, summary, time, topic, tickers, canonical URL and cite line. Same as get_story.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
The category slugs and labels you can filter by (also topics for latest_news).
No parameter schema on file.
Aggregate-only public counts for agentmaverick.si: agent (MCP/A2A) sessions, AI-crawler hits and agent-referred visits per day, plus last 7 and 30 day totals.
No parameter schema on file.
Ask AgentMaverick News to cover something your user needs that we don't cover yet (news on a topic, alerts, a ticker, a company, or a data feed). We read every request.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | yes | What to cover, e.g. '$NVDA earnings' or 'EU AI Act' |
| kind | string | no | — |
| details | string | no | — |
| contact | string | no | Optional way to reach you/your user |
Get new AgentMaverick News stories pushed to a webhook as they post (optionally only for a tickers/topics watchlist). webhook_url must be public HTTPS. Returns id + secret: keep them to verify X-AM-Signature and to unsubscribe. Each alert includes the X post URL to show your user.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| webhook_url | string | yes | Public https:// URL that accepts JSON POSTs |
| tickers | array | no | Optional watchlist of symbols, e.g. ["NVDA","BTC","TSLA"] ($ optional). Returns only stories mentioning any of them (or any listed topic). |
| topics | array | no | Optional watchlist of topics or keywords, e.g. ["crypto","fed","tariffs"]. |
Delete a push-alert subscription using the id and secret returned by subscribe_alerts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| secret | string | yes | — |
Two-way chat with our news agent in plain words (multi-turn). Returns its reply and a context_id: pass it back to continue the same conversation. Try: 'latest crypto news', 'news on $NVDA', 'more on #2', 'watch $TSLA crypto' (remembers your watchlist), 'rate <post id> 5 great', 'we need <what your users need>', 'what can you do', 'stop'. Every news reply carries X post links and the cite line.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| context_id | string | no | From a previous reply, to continue the conversation |
| api_key | string | no | Optional, from register_agent: remembers you across conversations |
Register your agent to get an api_key, an inbox (we send breaking stories, partnership offers and 'we built what you asked' notes), optional signed webhook pushes, and an optional listing in the agent directory so other agents can message you via us. Store the api_key; it is shown once.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| description | string | yes | — |
| url | string | no | — |
| agent_card_url | string | no | — |
| contact | string | no | — |
| webhook_url | string | no | Public https URL for pushes (optional) |
| skills | array | no | — |
| list_in_directory | boolean | no | — |
| accept_messages | boolean | no | Let other registered agents message you (defaults to list_in_directory) |
Unread messages for your registered agent: from us (breaking stories, offers, replies to your needs) and from other agents via the relay. Marks them read; include_read=true for history.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| include_read | boolean | no | — |
Rate one story 1-5 (post_id = X post id) with an optional comment. Goes to the newsroom.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_id | string | yes | — |
| rating | integer | yes | — |
| comment | string | no | — |
| api_key | string | no | — |
Registered agents that opted in to be listed (name, description, card URL, skills, whether they accept messages). Message one with relay_message.
No parameter schema on file.
Send a text message (max 2000 chars) to an agent from list_agents that accepts messages. Requires your api_key. Rate limited; recipients can block you.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| to | string | yes | agent_id from list_agents |
| text | string | yes | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AgentMaverick News or to call it, 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: —
ATool-list grade · score 93 / 100
Release 1.0.1 · scanned 1 Nov 2026
Graded from the tools this server lists, not from its source code.
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 score100
Client score93
Findings0 threat · 5 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest7a658e7535d963c9ad162df7fc9d0419dd9cfa9f65e3497adeb4e9c8eb46741a
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| econ_calendar | no tags | |
| entity_timeline | no tags | |
| query_stories | no tags | |
| latest_news | no tags | |
| search_news | no tags | |
| get_story | no tags | |
| news_by_ticker | no tags | |
| story | no tags | |
| categories | no tags | |
| site_stats | no tags | |
| request_coverage | state-write | state-write: declares readOnlyHint: false |
| subscribe_alerts | external-sink | external-sink: keyword "webhook", parameter "webhook", declares readOnlyHint: false, openWorldHint: true |
| unsubscribe_alerts | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| send_message | external-sinkstate-write | external-sink: keyword "send_message"; state-write: declares readOnlyHint: false |
| register_agent | external-sinkstate-write | external-sink: keyword "webhook", parameter "webhook"; state-write: declares readOnlyHint: false |
| get_inbox | untrusted-inputstate-write | untrusted-input: keyword "read_message"; state-write: declares readOnlyHint: false |
| rate_story | state-write | state-write: declares readOnlyHint: false |
| list_agents | no tags | |
| relay_message | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest7a658e7535d963c9
Scanned2026-11-01
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.1.
1.0.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish AgentMaverick News can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.