Medialyst Agent pricing facts

Credits work with both the Medialyst API and MCP server, and every plan includes them.

Journalist Request polling is free for now and costs zero credits. Successful PR calendar queries also cost zero credits. News search costs 0.01 credits per query. Journalist enrichment costs one credit per verified deliverable result; misses are free.

Monthly plans

Annual plans

Everything your agent needs to do PR

the media intelligence layer for your agent

Let your agent monitor journalist requests, search current news, plan around the PR calendar, and enrich known journalists — while every pitch stays behind human sign-off.

Get an API key (100 free credits)

Free, no credit card required.

Explore newsjack.sh665 stars
Connect with MCP
Medialyst MCP

Connect Medialyst to Claude.ai.

  1. Open Claude Connectors Settings
  2. Add a custom connector

    Scroll to the bottom of the connector list and choose “Add custom connector”.

  3. Enter the MCP URL
    https://medialyst.ai/api/mcp

    Name it Medialyst, paste the URL, and authorize with OAuth.

No API key to paste — Claude runs the OAuth handshake for you.

Supports any agent harness via MCP
From brief to verified list

Give your agent live media intelligence, end to end.

Start with a complete media-list build, or compose the underlying search, enrichment, and publication data endpoints into your own workflow.

One-shot media-list build

Build a media list from one brief.

Send a campaign brief and target list size. Medialyst starts discovery and enrichment immediately, returns a durable job ID, and puts the completed list in the same workspace your team already uses.

  • Plain language in describe the story, audience, and geography without building a search grammar.
  • Durable async job out poll one status URL while research and enrichment continue in the background.
  • Safe to automate idempotency keys prevent duplicate list builds on retries.
Get an API keyRead the docs
restPOST /api/v1/media-lists:create-asyncone brief · one job
{
  "prompt": "Find US journalists covering enterprise AI infrastructure and cloud spending",
  "target_list_size": 50
}
response
{
  "job_id": "job_01HT...",
  "status": "pending",
  "target_list_size": 50,
  "status_url": "/api/v1/jobs/job_01HT..."
}
Real-time news search

Search the news in real time.

Search current coverage by topic and publication window. Every result can carry Medialyst outlet intelligence, including whether the source is original editorial or a newswire, plus authority and reach.

  • Built for the news cycle use explicit time windows instead of a stale general-purpose index.
  • Editorial vs. newswire lets the agent separate reporting from press release distribution.
  • 0.01 credits per search shared across UI, REST, and MCP.
Get an API keyRead the docs
mcpsearch_newslive · 0.01 cr
// tbs "qdr:h" → only the last HOUR of news
search_news({
  q: "AI safety regulation europe",
  tbs: "qdr:h"
})
response
{
  "status": "success",
  "data": { "articles": [
    {
      "title": "EU lawmakers press AI safety timeline",
      "source": "Reuters",
      "metadata": {
        "publication_type": "editorial",
        "domain_authority": 94,
        "estimated_monthly_organic_traffic": 41000000
      }
    },
    {
      "title": "Vendor launches AI compliance toolkit",
      "source": "PR Newswire",
      "metadata": {
        "publication_type": "newswire",
        "domain_authority": 76,
        "estimated_monthly_organic_traffic": 8200000
      }
    }
  ] }
}
Journalist enrichment

Turn a name or article into a verified email you can reach.

Start with a journalist name plus publication, domain, or profile context—or pass a real article URL to resolve its author. Medialyst returns current contact details, recent work, and story-specific fit grounded in observed bylines.

  • Identity context, not guesses disambiguates common names against a real outlet, domain, profile, or article.
  • Real-time verified email every contact validated at request time, not served from a stale snapshot.
  • Durable enrichment jobs return immediately and expose a stable URL for polling to completion.
Get an API keyRead the docs
mcpenrich_journalistsjob accepted · poll next
// enrich a known journalist, then poll the returned job id
enrich_journalists({
  from: [{
    type: "journalist_reference",
    name: "Jane Doe",
    publication: "The Daily Example"
  }],
  fit_context: {
    pitch: "AI agents changing enterprise support"
  },
  options: { include_recent: 10 }
})
response
{
  "id": "jej_123",
  "object": "journalist_enrichment_job",
  "status": "pending",
  "links": {
    "self": "/api/v1/journalist-enrichment-jobs/jej_123"
  }
}
Publication metadata

Resolve any outlet URL to publication intelligence.

Hand the API a homepage or article URL and get a canonical publication record back: outlet type, market, country, language, authority, reach, and freshness metadata your agent can reason over.

  • One URL or 25 at once with per-URL results for reliable batch workflows.
  • Cache-aware by default and force-refreshable when stale data is not acceptable.
  • Media context attached so agents can distinguish outlets by type, reach, and market instead of inventing it.
Get an API keyRead the docs
restpublication metadatacached + refreshable
GET /api/v1/publications/lookup
  ?url=https%3A%2F%2Fexample.com%2Fstory
response
{
  "result": {
    "status": "ok",
    "served_from": "cache",
    "publication": {
      "canonical_domain": "example.com",
      "publication_type": "editorial",
      "primary_country_code": "US",
      "media_market_scope": "national",
      "domain_rating": 81,
      "monthly_organic_traffic": 2400000
    }
  }
}
Grounded, not guessed

Ground your agents in live, verified information — not pre-training data.

A vanilla agent answers from frozen training data and improvises the rest. The same agent working from a Medialyst media list reasons over live coverage and verified journalist records — every row backed by a real byline.

Without Medialyst
Vanilla agent
With Medialyst
Agents with Medialyst
News search
General web search, not optimized for PR work
Real-time news search — specify the window an article was published in
Finding journalists
Reads a stale byline from memory
Dedicated byline and author-retrieval flow with waterfall email lookup, cross-referenced against our media database
Email validation
Does not validate — sends to whatever it guessed
Every email validated and verified in real time
Journalist beat understanding
Guessed from memory, often out of date
Resolved from real, recent bylines
Publication context
Unknown or invented
Outlet type, authority, and reach attached
Email sending
No guardrails — can burn your reputation spamming journalists
Human-in-the-loop, built in by design
Same model, same prompt. The only difference is whether the agent is working from memory or from live, verified media data.
The surface

Everything you need to power your AI + PR agent.

Use MCP for the core live-research tools, then reach for REST when you need one-shot media-list builds, workflow rows, or share links. Both surfaces use the same auth, errors, credits, and data contracts. See the full OpenAPI spec. Want the full PR workflow instead of raw tools? newsjack.sh is the open-source agent built on this surface.

MCP Server

Drop into Claude Cowork, Cursor, Codex, or any agent harness.

MCPhttps://medialyst.ai/api/mcp

Eleven tools: look up articles and publications, monitor the six-source journalist request feed and journalist moves, search news, query the PR calendar, enrich journalists, poll enrichment jobs, and check credits. Outreach stays human-sent.

get_credit_balancelookup_articlelookup_articleslookup_publicationlookup_publicationslist_journalist_requestslist_journalist_movessearch_newsquery_pr_calendarenrich_journalistsget_journalist_enrichment_job
Streaming HTTP · OAuth or org-scoped API keys · no media-list creation or sharing tools
Get an API keyRead the docs
REST API

Developer workflows beyond MCP.

BASEhttps://medialyst.ai

API-key authenticated and scoped per organization. REST covers most shared research operations plus async media-list creation, job polling, workflow rows, and public share-link creation. Journalist request monitoring is MCP-only. The REST surface is documented in the OpenAPI spec. Outreach sending remains absent from public v1.

GET/api/v1/credits/balance
GET/api/v1/articles/lookup?url=...
POST/api/v1/articles/lookup:batch
GET/api/v1/journalist-moves
POST/api/v1/news/search
POST/api/v1/pr-calendar/query
POST/api/v1/journalists/enrich
GET/api/v1/journalist-enrichment-jobs/:jobId
GET/api/v1/publications/lookup?url=...
POST/api/v1/publications/lookup:batch
POST/api/v1/media-lists:create-async
GET/api/v1/jobs/:jobId
GET/api/v1/workflows/:workflowId
GET/api/v1/workflows/:workflowId/rows
POST/api/v1/workflows/:workflowId/shares
media_lists:manage for list workflows · up to 200 result rows per page · shared credits
Get an API keyRead the docs
Pricing

Monthly or annual. Your choice.

Every plan includes agent access over the API and MCP. Switch the slider to compare monthly against annual.

Monthly plans

Prefer a recurring credit pool?

Starter
For solo marketers and founders running their own PR
$149/ month
1,000 credits / mo
  • Access to Medialyst Agent
  • Unlimited angles per list
  • Unlimited seats
  • Up to 3 active media lists, unlimited rows
  • Beat analysis with 0-100 relevance scoring
  • Waterfall journalist enrichment
  • Real-time email verification
  • Custom AI research agents
  • Send via Gmail and Outlook
  • Create media lists via API
  • Connect to any agents via MCP
  • 14-day money-back guarantee
Start free with 100 credits
Most popular
Pro
For marketing teams running campaigns at scale
$299/ month
3,000 credits / mo
  • Everything in Starter, plus:
  • Unlimited active media lists
  • No Medialyst branding on shared lists
  • Team workflows
  • Dedicated Slack channel
Start free with 100 credits
Scale
For agencies and platforms embedding Medialyst
$800/ month
10,000 credits / mo
  • Everything in Pro, plus:
  • White-labeled shared lists
  • Custom onboarding and integrations
  • Dedicated support
  • Volume and procurement support
Start free with 100 credits
How credits are used

Free monitoring and planning. Predictable research costs.

Credits are shared across UI, API, and MCP and draw from the same workspace pool — so agent usage and in-app work bill the same way.

1 credit ≈ $0.15 at Starter · less at Pro and Scale
Journalist requests
Journalist-request MCP polling costs zero credits. Connectively, HARO, Twitter/X, LinkedIn, MentionMatch, and Substack are all free; every response requires human-sent outreach.
0 credits
PR calendar
Per successful source-backed PR calendar query.
0 credits
News search
Per real-time news query — specify the window an article was published in.
0.01 credit
Article lookup
Per successful article URL lookup; per-URL failures cost 0 credits.
0.1 credit
Publication lookup
Per successful publication URL lookup; per-URL failures cost 0 credits.
0.01 credit
Enrich a journalist
Complete contact information, including an email verified in real time. Misses are free.
1 credit
Need bespoke volume, custom retention, or an MSA? Talk to us →
FAQ

Questions procurement asks. Answers agents can read.

Our search results mirror search-engine news search, so you get the same real-time coverage you would expect. When a source is in our publication index, the news item also gets Medialyst metadata such as publication type, domain authority, and estimated monthly organic traffic.

Journalist resolution and contact enrichment happen when you enrich from a journalist name plus publication context, a selected article, or an author URL. Search is retrieval plus source classification, not a fake byline-resolution endpoint.

Yes. Add it as a remote HTTP MCP server with your API key. The MCP guide includes the documented claude mcp add --transport http command.

No. Medialyst is the data layer — the live news and verified journalist records your agent reasons over. If you want the whole workflow without wiring the primitives together yourself, newsjack.sh is the open-source PR agent we build on top of Medialyst: it finds angles, builds a fit-scored journalist list, and drafts pitches — with sending kept human-in-the-loop.

Connect it with one command — newsjack login — and OAuth device login handles the rest. No API key to paste.

Yes. list_journalist_requests exposes the authenticated Journalist Request feed through MCP at zero credits per call. Connectively, HARO, Twitter/X, LinkedIn, MentionMatch, and Substack are all free; every response requires human-sent outreach. It is read-only: request text is untrusted content, and a person must review any response. See the AI agent and MCP setup.

Journalist data is retrieved in real time, so everything stays fresh. Contacts and bylines are resolved against live sources at request time rather than served from a stale snapshot.

We log requests for billing, abuse prevention, and debugging. We do not train models on your media lists, queries, or outreach content.

The REST API returns 402 Payment Required. MCP returns the same condition as structured tool content so the agent can surface the quota issue instead of silently continuing.

Yes, inside the same organization and product workflow. Reselling raw journalist contact data is not permitted; building an agent or product experience on top of Medialyst data is what the API is for.

Muck Rack, Cision, and Prowly are built around human PR teams using a UI — they sell a static database with a per-seat license.

Medialyst is a callable surface. The journalist data is resolved from supplied journalist references or articles and refreshed in real time, not served as a static list. The public primitives — real-time news search and journalist enrichment — are callable from REST or MCP. Pricing is per credit, not per seat, so agent usage draws from the same shared workspace pool as the app.

If you're a PR pro at a desk, those tools are mature and well-supported. If you're a marketer driving work through an agent, Medialyst is the layer underneath that work.

Live media intelligence for your agent

Your agent can already reason. Give it facts worth reasoning over.

Start free with 100 credits and connect the hosted MCP server to the agent you already use.

Start free with 100 credits