Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Purefeed 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.
96/100
trust score
1
downloads a day
local
runs on your machine
45
downloads in 30d
What it does
MCP server for Purefeed — AI-powered Twitter/X feed intelligence
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user purefeed-mcp '--' npx -y @purefeed/mcp-server
# 2 — ask your agent for something these tools do
# get_me, get_feed, get_signal_insights and 16 more
Purefeed costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
PUAll 1 server
@purefeed1 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 Purefeed 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. Its scan result is on the Security tab — 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. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user purefeed-mcp '--' npx -y @purefeed/mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: 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 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
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.
Get your Purefeed user profile including id, email, and account creation date. Use this to verify the API key works.
No parameter schema on file.
Retrieve your tweet feed ranked by AI signal relevance. Returns tweets with text, author, engagement metrics (views, replies, retweets), and signal matches. Use search param for text filtering, signal_ids to filter by specific signals.
No parameter schema on file.
Get AI signal analysis for specific tweets. Returns signal name, AI-generated insight content, sentiment, industry category, content type, and engagement type for each match. Pass tweet_ids from get_feed or search results.
No parameter schema on file.
List your bookmark folders. Returns id, name, and created_at for each folder. Use folder IDs with get_folder_tweets.
No parameter schema on file.
Get tweets saved in a bookmark folder. Returns tweet_id, full_text, creation_date, favorites, retweets, and views. Call list_folders first to get valid folder IDs.
No parameter schema on file.
List all your AI signal configurations. Returns id, user_signal_name, signal_description, and creation_date. Signal IDs are needed for get_signal, update_signal, delete_signal, and get_signal_matches.
No parameter schema on file.
Create a new AI signal that automatically detects and tags matching tweets in your feed. Provide a descriptive name and natural-language description of what to detect (e.g. 'Startup funding announcements over $10M'). Optionally add tags and keyword filters. Note: it takes up to 6 hours for the…
No parameter schema on file.
Get details of a specific signal including its configuration, color, cron schedule, timezone, and keyword filters. Call list_signals first to get valid signal IDs.
No parameter schema on file.
Update an existing signal's name or description. The signal will re-process tweets with the new criteria on its next cron run.
No parameter schema on file.
Permanently delete an AI signal. This cannot be undone — all signal match history is lost. Use list_signals first to confirm the signal_id.
No parameter schema on file.
Get tweets that triggered a specific signal. Returns the same data structure as get_feed but filtered to a single signal. Call list_signals first to get valid signal IDs.
No parameter schema on file.
List available writing styles (both system defaults and your custom styles). Returns id, name, instructions, and is_default. You MUST call this before generate_post to get a valid styleId.
No parameter schema on file.
Semantic search across all your saved tweets using natural language. Uses vector embeddings for meaning-based matching, not just keywords. Returns tweets ranked by relevance with the same structure as get_feed.
No parameter schema on file.
Generate a tweet or thread using AI based on reference tweets and/or a freeform idea. Requires a styleId from list_styles. Provide either tweetIds (from get_feed, search_tweets, etc.) or ideaPrompt, or both. Returns the generated text as a stream.
No parameter schema on file.
Score a post for AI-likeness (1-100) and optionally rewrite it to sound more human. If score <= 30, the post sounds human already and no rewrite is returned. If score > 30, a rewritten version is provided. Response format: first line is JSON {score, reasons}, followed by the rewritten text if…
No parameter schema on file.
Publish a post to X/Twitter immediately via Typefully. Requires a Typefully connection configured in Purefeed settings. Multiple strings create a thread. If you get 'No Typefully connection' error, tell the user to connect Typefully in their Purefeed settings.
No parameter schema on file.
Schedule a post for a specific time via Typefully. Requires Typefully connection. Use ISO 8601 datetime format for scheduled_at.
No parameter schema on file.
Save a post as a draft in Typefully for later editing and publishing. Requires Typefully connection.
No parameter schema on file.
Add a post to the next available slot in your posting queue. Uses Typefully if connected, otherwise falls back to Purefeed's internal scheduling based on your posting slots.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- 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 Purefeed 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: —
ATrust score 96 / 100
Release 0.1.0 · scanned 15 Oct 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 score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest4504934e8f77cf62a9cd85b46f7de88d32a12228e37367e4869e3b7f14b33508
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 (19 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_me | no tags | |
| get_feed | no tags | |
| get_signal_insights | no tags | |
| list_folders | no tags | |
| get_folder_tweets | no tags | |
| list_signals | no tags | |
| create_signal | state-write | state-write: declares readOnlyHint: false |
| get_signal | no tags | |
| update_signal | state-write | state-write: declares readOnlyHint: false |
| delete_signal | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| get_signal_matches | no tags | |
| list_styles | no tags | |
| search_tweets | no tags | |
| generate_post | external-sink | external-sink: keyword "tweet" |
| humanize_post | no tags | |
| publish_post | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| schedule_post | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| save_draft | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| queue_post | 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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest4504934e8f77cf62
Scanned2026-10-15
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
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 Purefeed 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.