Proofite MCP server
✓ VerifiedLets an AI agent read personal daily briefings and retune information filters including newsletters, RSS feeds, and web searches.
Also known as hanicker/proofite-mcp, proofite-mcp
- Stars
- 0
- Tools
- 27
- Downloads, 30 days
- —
- Latest version
- 1.2.0
- Last commit
- Aug 17, 2026
- License
- MIT
What is Proofite MCP?
Proofite lets an AI agent read personal daily briefings and retune information filters including newsletters, RSS feeds, and web searches. It exposes 27 tools, such as get_briefing, list_briefings, get_information_diet.
Summary generated from the project's README
About Proofite MCP server
Proofite allows AI agents to manage a personalized information diet by interacting with a daily briefing system. This system aggregates content from newsletters, RSS feeds, and monitored web searches into a single markdown digest or an audio podcast. Users can connect via a remote HTTP transport using an authorization bearer token or through a stdio bridge using an API key. This setup enables an agent to act as an editor for the user's news consumption.
Developers can use specific tools to adjust how information is filtered. The server provides capabilities to read existing briefings, inspect the current information diet, and manage various sources. Beyond simple reading, the server supports writing actions such as tuning specific topics, correcting the briefing through natural language notes, and requesting deep-dive research on new subjects. It is designed to be the same engine that drives the Proofite product itself, ensuring that agent-driven adjustments to topic weights, technical depth, and delivery schedules are reflected in future briefings.
What you can do with it
- 1Adjust news topic densityTell the agent to reduce coverage of a specific subject like cryptocurrency in future briefings.
- 2Request deep researchInstruct the AI to perform fresh web research on a specific topic for the next briefing.
- 3Manage information sourcesHave the agent add new RSS feeds or monitor specific Google queries to expand the news diet.
Written from the project's README. Every use case is checked against a quote from it.
How to install Proofite MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Proofite MCP in Claude Code
$ claude mcp add --env 'PROOFITE_API_KEY=<YOUR_PROOFITE_API_KEY>' proofite-mcp -- npx -y proofite-mcpInstall Proofite MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"proofite-mcp": {
"command": "npx",
"args": [
"-y",
"proofite-mcp"
],
"env": {
"PROOFITE_API_KEY": "<YOUR_PROOFITE_API_KEY>"
}
}
}
}Install Proofite MCP in VS Code
.vscode/mcp.json
{
"servers": {
"proofite-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"proofite-mcp"
],
"env": {
"PROOFITE_API_KEY": "<YOUR_PROOFITE_API_KEY>"
}
}
}
}Install Proofite MCP in VS Code CLI
$ code --add-mcp '{"name":"proofite-mcp","type":"stdio","command":"npx","args":["-y","proofite-mcp"],"env":{"PROOFITE_API_KEY":"<YOUR_PROOFITE_API_KEY>"}}'Install Proofite MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"proofite-mcp": {
"command": "npx",
"args": [
"-y",
"proofite-mcp"
],
"env": {
"PROOFITE_API_KEY": "<YOUR_PROOFITE_API_KEY>"
}
}
}
}Install Proofite MCP in Codex
$ codex mcp add proofite-mcp --env 'PROOFITE_API_KEY=<YOUR_PROOFITE_API_KEY>' -- npx -y proofite-mcpInstall Proofite MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.proofite-mcp] command = "npx" args = ["-y", "proofite-mcp"] [mcp_servers.proofite-mcp.env] PROOFITE_API_KEY = "<YOUR_PROOFITE_API_KEY>"
Install Proofite MCP in Gemini CLI
$ gemini mcp add -s user -e 'PROOFITE_API_KEY=<YOUR_PROOFITE_API_KEY>' proofite-mcp npx -- -y proofite-mcpInstall Proofite MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"proofite-mcp": {
"command": "npx",
"args": [
"-y",
"proofite-mcp"
],
"env": {
"PROOFITE_API_KEY": "<YOUR_PROOFITE_API_KEY>"
}
}
}
}Proofite MCP tools 27
Detected from the READMEget_briefinglist_briefingsget_information_dietlist_sourcesget_sourceget_podcast_episodelist_read_laterlist_deep_divesget_accountupdate_information_diettune_topiccorrect_briefing
| get_briefing | — | |
| list_briefings | — | |
| get_information_diet | — | |
| list_sources | — | |
| get_source | — | |
| get_podcast_episode | — | |
| list_read_later | — | |
| list_deep_dives | — | |
| get_account | — | |
| update_information_diet | — | |
| tune_topic | — | |
| correct_briefing | — |
Show all 27 toolsShow fewer tools
rate_briefing_entryset_learned_profilerequest_deep_divesave_for_latergenerate_briefingcreate_sourceupdate_sourcedelete_sourceadd_feedremove_feedadd_web_searchremove_web_searchdiscover_sourcesimport_opmlunsubscribe_newsletter
| rate_briefing_entry | — | |
| set_learned_profile | — | |
| request_deep_dive | — | |
| save_for_later | — | |
| generate_briefing | — | |
| create_source | — | |
| update_source | — | |
| delete_source | — | |
| add_feed | — | |
| remove_feed | — | |
| add_web_search | — | |
| remove_web_search | — | |
| discover_sources | — | |
| import_opml | — | |
| unsubscribe_newsletter | — |
Configuration
PROOFITE_API_KEYRequiredSecretYour Proofite API key, created at https://proofite.com/app/settings → Connections
| Name | Description | |
|---|---|---|
| PROOFITE_API_KEY | Your Proofite API key, created at https://proofite.com/app/settings → Connections | RequiredSecret |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablehanicker/proofite-mcp is public and reachablegithub.com/hanicker/proofite-mcp ↗Pass
- Package names this repository as its sourceproofite-mcp names hanicker/proofite-mcp as sourcenpmjs.com/package/proofite-mcp ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-06github.com/hanicker/proofite-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from proofite-mcpPass
- No critical advisory in the package or its dependencies1 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model27 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 118 msPass
README
View on GitHubProofite MCP server
Give your AI assistant the keys to your information diet.
Proofite turns the sources you choose — newsletters, RSS feeds, monitored web searches, saved links — into one personal briefing every morning, written by AI and available as a podcast. This MCP server lets any agent read that briefing and, more importantly, retune the filter behind it: what gets in, how deep, how technical, how often, and what never appears again.
It is the same server the product uses for its own voice mode, so it is not a demo surface: it is how Proofite is driven.
you → "too much crypto this week, and go deeper on the EU regulation"
agent → correct_briefing(note: "…")
→ topic weights adjusted, depth raised, deep dive queued
→ tomorrow's briefing is different
Install
Remote (recommended). Streamable HTTP, no install. Create a key in Proofite under Settings → Connections, then:
claude mcp add --transport http proofite https://proofite.com/mcp \
--header "Authorization: Bearer pfk_live_…"
Or in any client that reads a JSON config:
{
"mcpServers": {
"proofite": {
"type": "http",
"url": "https://proofite.com/mcp",
"headers": { "Authorization": "Bearer pfk_live_…" }
}
}
}
stdio bridge, for clients that do not speak HTTP yet:
{
"mcpServers": {
"proofite": {
"command": "npx",
"args": ["-y", "proofite-mcp"],
"env": { "PROOFITE_API_KEY": "pfk_live_…" }
}
}
}
Tools
| Tool | What it does | |
|---|---|---|
get_briefing |
read | Read the user's personal AI-written news briefing (daily digest) in full markdown: every story selected today from their newsletters, RSS feeds and monitored web searches, with sources. Returns the latest briefing by default, or a specific one by id or date. Also returns an index of entry ids, needed to rate or correct individual stories. |
list_briefings |
read | List the user's past daily briefings (most recent first) with date, title, number of stories and whether an episode exists. Use it to find the id of a specific day before reading or correcting it. |
get_information_diet |
read | Read everything that shapes what reaches this person: delivery schedule, length, technicality, depth, stance and tone, stated interests and no-go topics, the profile the system has learned about them, and the per-topic preferences built from their feedback (affinity, muted, followed). This is the full picture of their news filter — read it before changing anything. |
list_sources |
read | List the topic inboxes this person feeds their briefing with: each one has a dedicated email address for newsletter subscriptions, plus RSS feeds and monitored web searches. Shows how much each produced recently, its priority and whether it is included in the briefing. |
get_source |
read | Inspect one topic inbox in detail: every RSS feed (with its health and last fetch), every monitored web search, X/Twitter profiles, and the newsletters currently arriving at its dedicated address. Use it before removing or reorganising anything. |
get_podcast_episode |
read | Get the audio episode generated from a briefing: a private podcast narrated in the user's language, with a playable URL and the show notes listing every source. Returns the latest episode by default. |
list_read_later |
read | List what is queued in the read-later inbox: links and forwarded emails that are guaranteed to be covered in the next briefing. |
list_deep_dives |
read | List the deep-dive research requests waiting to be covered: topics the user asked the briefing to investigate with fresh web research. |
get_account |
read | Account status: plan, whether the briefing is currently running, when the next one is due, how many sources and stories are in the system, and the AI cost accrued this month. |
update_information_diet |
write | Change how and when the briefing reaches this person: delivery time and days, length, technicality, depth, stance, tone, stated interests and topics to avoid, language, timezone, podcast and email delivery. Pass only the keys you want to change. Read get_information_diet first — these are global settings, not per-topic ones (for a single topic use tune_topic). |
tune_topic |
write | Tune how a single topic is treated in future briefings: more or less of it, more or less technical, deeper or shorter, more or less often, muted entirely, or followed so every development gets reported. This is the precise instrument — for a vague comment like "too much crypto lately" use correct_briefing instead. |
correct_briefing |
write | Tell the briefing what was wrong with it, in plain language — "too much crypto and not enough on the EU regulation", "keep it shorter", "explain the technical parts more simply", "follow this story". An AI editor reads the note against the actual briefing and turns it into concrete adjustments: topic preferences, settings, deep-dive requests. This is the main way a person retunes their news feed by talking. |
rate_briefing_entry |
write | Give a precise up/down signal on one story of a briefing: more like this, less like this, more technical, simpler, deeper, shorter, follow it, or mute its topics. Applies to the topics of that story, so the next briefing weighs them differently. |
set_learned_profile |
write | Read or rewrite the free-text profile the briefing uses to know who this person is — their work, projects, recurring interests, what they already know. Appending is usually better than replacing: pass mode "append" to add a line. |
request_deep_dive |
write | Ask the next briefing to investigate a topic properly, with fresh web research: it will include a mini-dossier with sources. Use it whenever the person says "I want to know more about X" or "keep digging on this". |
save_for_later |
write | Put a link or a note into the read-later queue: whatever lands there is guaranteed to be covered in the next briefing. The page is fetched and its text stored, so it can be summarised even if the site later blocks access. |
generate_briefing |
write | Generate a briefing immediately instead of waiting for the scheduled time, using everything collected so far. Costs real AI money and takes a couple of minutes, so use it only when explicitly asked. Returns the id to poll with get_briefing. |
create_source |
write | Create a new topic inbox: a themed container with its own dedicated email address (subscribe newsletters to it), which can hold RSS feeds and monitored web searches. This is how you add a whole new subject to someone's information diet. |
update_source |
write | Change a topic inbox: rename it, change its description, raise or lower its priority in the briefing, set a per-inbox technicality level, temporarily exclude it from the briefing or pause it entirely. |
delete_source |
write | Permanently delete a topic inbox with all its feeds, searches and collected content. Irreversible: the dedicated email address stops working too. Prefer update_source with is_active false when in doubt. |
add_feed |
write | Add an RSS/Atom feed to a topic inbox. You can pass the site address instead of the feed URL — the server fetches the page and discovers the feed. If it fails, the reason is precise (blocked by the site, gone, unreadable) so it can be reported honestly. |
remove_feed |
write | Remove an RSS feed from a topic inbox. Already-collected content stays; nothing new arrives from it. |
add_web_search |
write | Monitor a Google query every day and feed the results into a topic inbox: the standing-search way to follow a company, a person, a law or a niche subject that has no RSS feed. kind "news" watches the news index, "search" the whole web. |
remove_web_search |
write | Stop monitoring a standing web search: no new results from that query will reach the briefing. What it already collected stays where it is. |
discover_sources |
read | Describe a subject in plain words and get back real, working sources for it: RSS feeds validated live by the server (dead ones are dropped before you see them), web searches worth monitoring, and newsletters worth subscribing to. Nothing is added — it returns proposals to pass to add_feed / add_web_search. |
import_opml |
write | Import subscriptions from another RSS reader (Feedly, Inoreader, FreshRSS, NetNewsWire) by passing the OPML file contents. Set dry_run true first to see what is in it and what is already present; then run it for real to add them (they are validated one by one, and the ones that fail come back with the reason). |
unsubscribe_newsletter |
write | Unsubscribe from a newsletter arriving in one of the inboxes. When the sender supports one-click unsubscribe the server does it directly; otherwise it returns the URL a human has to open, and says so honestly. |
It also exposes resources (proofite://briefing/latest, proofite://diet, proofite://sources) and two prompts (tune-my-feed, catch-me-up).
Notes that matter
- Keys can be read-only, and the server enforces it: a read-only key cannot change a setting however convincingly it is asked. Create one per client, revoke individually.
- Changes apply from the next briefing, never retroactively.
- Scoped to one account. The key identifies a person; the server has no way to reach anyone else's information.
- Protocol. Streamable HTTP. Speaks the
2026-07-28revision (stateless, per-request_meta, mirroredMcp-Method/Mcp-Nameheaders,server/discover) and the olderinitializehandshake used by most clients today — it detects which era you speak from your first request.
Requirements
A Proofite account — free trial, no card. The briefing, the podcast and this server are the same product seen from three sides.
Links
- proofite.com/mcp — live documentation, generated from the server's own tool registry
- proofite.com — what Proofite is
https://proofite.com/.well-known/mcp.json— machine-readable manifest
MIT © Nicola Moretti mcp-name: com.proofite/proofite
Proofite MCP questions
How do I add Proofite MCP to Claude Code?
Run claude mcp add --env 'PROOFITE_API_KEY=<YOUR_PROOFITE_API_KEY>' proofite-mcp -- npx -y proofite-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Proofite MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Proofite MCP provide?
It exposes 27 tools, including get_briefing, list_briefings, get_information_diet, list_sources, get_source.
Can the AI agent change my news settings?
Yes, the agent can use tools like correct_briefing and tune_topic to adjust topic weights, depth, and technicality.