Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
ThinkRun 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
trust score
5
downloads a day
local
runs on your machine
216
downloads in 30d
What it does
Connects AI coding agents to the user's real Chrome browser with real sessions and cookies so they can test their own frontend work.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user thinkrun-mcp '--' npx -y @thinkrun/mcp
# 2 — ask your agent for something these tools do
# recording_upload, session_create, session_status and 64 more
ThinkRun costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
THAll 1 server
@thinkrun1 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 ThinkRun 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 thinkrun-mcp '--' npx -y @thinkrun/mcpReconnect, 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
67 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.
Upload an explicit local .webm, .mp4, or .mov file as a feedback recording. Bytes are streamed directly to the recording API, never through MCP or the browser bridge.
No parameter schema on file.
Create a new browser session. Returns a sessionId to use with all other tools.
No parameter schema on file.
Get the current status of a browser session including URL, title, and action count.
No parameter schema on file.
Terminate a browser session and clean up resources. Artifacts are preserved.
No parameter schema on file.
List all active browser sessions for this user.
No parameter schema on file.
List artifacts (screenshots, recording) for a session.
No parameter schema on file.
Poll session status until the session is ready (running/active) or timeout.
No parameter schema on file.
Set the default session for subsequent tool calls so you do not need to pass sessionId every time.
No parameter schema on file.
Enable or disable local audit mode for the current local tab-backed session.
No parameter schema on file.
Switch the MCP server between local (Chrome extension) and cloud (ThinkRun API) modes at runtime.
No parameter schema on file.
Return the authenticated hosted remote-agent identity and current user-link status.
No parameter schema on file.
Request a user-approved hosted remote browser-control grant for the current remote agent.
No parameter schema on file.
Poll the status of a hosted remote browser-control request and any approved grant.
No parameter schema on file.
Cancel a pending hosted remote browser-control request or revoke an active grant.
No parameter schema on file.
Stateless: fetch rendered HTML for a URL without a browser session (no sessionId).
No parameter schema on file.
Stateless: extract plain text for a URL without a browser session. POST /api/cache/text.
No parameter schema on file.
Stateless: capture a PNG for a URL without a session. Returns JSON with artifactUrl when Accept is application/json.
No parameter schema on file.
Navigate the browser to a URL. Waits for page load before returning.
No parameter schema on file.
Navigate back to the previous page in browser history.
No parameter schema on file.
Navigate forward to the next page in browser history.
No parameter schema on file.
Wait for an element to appear on the page. Useful after navigation or clicking
No parameter schema on file.
Click an element on the page using a CSS selector.
No parameter schema on file.
Click at viewport-relative CSS pixel coordinates. Local mode only.
No parameter schema on file.
Type text into an input, textarea, or contenteditable element; local extension mode also supports role=textbox.
No parameter schema on file.
Direct replacement for an input, textarea, or contenteditable element; local extension mode also supports role=textbox.
No parameter schema on file.
Press a keyboard key. Common keys: Enter, Tab, Escape, ArrowDown, ArrowUp, Backspace.
No parameter schema on file.
Scroll the page or a specific element. Positive y scrolls down, negative scrolls up.
No parameter schema on file.
Hover the mouse over an element. Useful for triggering tooltips or dropdown menus.
No parameter schema on file.
Select an option from a <select> dropdown element.
No parameter schema on file.
Get an accessibility tree snapshot of the current page. This is a lightweight
No parameter schema on file.
Capture a screenshot of the current page. Returns an image plus any available artifact metadata.
No parameter schema on file.
Extract content from the page. Types: "text" for visible text, "html" for raw HTML,
No parameter schema on file.
Execute JavaScript in the browser page context. The script runs in the page,
No parameter schema on file.
List all open browser tabs. Local mode only.
No parameter schema on file.
Open a new browser tab, optionally navigating to a URL. Local mode only.
No parameter schema on file.
Close a browser tab by ID. If no tabId is provided, closes the current tab. Local mode only.
No parameter schema on file.
Attach to an existing local Chrome tab by tab ID and make it the default session. Local mode only.
No parameter schema on file.
Switch the active local Chrome tab without rebinding the current default session. Local mode only.
No parameter schema on file.
Bring the currently bound local browser tab/window to the foreground without rebinding the default session. Local mode only.
No parameter schema on file.
Open a new local Chrome window and bind the resulting tab as the default session. Local mode only.
No parameter schema on file.
Release the current local tab ownership without closing the tab. Clears the default session when releasing the bound local session. Local mode only.
No parameter schema on file.
Return structured local continuity, ownership, reclaim, and bridge recovery diagnostics. Local mode only.
No parameter schema on file.
Trigger the bounded native-host reset-connection recovery path used for false local circuit-breaker trips. Local mode only.
No parameter schema on file.
Return the current page URL for the active session.
No parameter schema on file.
Return the current page title for the active session.
No parameter schema on file.
Return the current page HTML for the active session. Large documents are truncated explicitly in the response.
No parameter schema on file.
Pause for a bounded duration in milliseconds (max …).
No parameter schema on file.
Check for pending browser dialogs (alert, confirm, prompt) and view dialog history.
No parameter schema on file.
Accept or dismiss a pending browser dialog (alert, confirm, prompt).
No parameter schema on file.
Wait for specific text to appear on the page.
No parameter schema on file.
Get browser console messages (log, warn, error) from the current session.
No parameter schema on file.
Get network requests made by the browser during this session.
No parameter schema on file.
Clear console and network logs for the session.
No parameter schema on file.
Run a direct native-host action against the currently attached local tab.
No parameter schema on file.
Check the status of a previously started local action. Local mode only.
No parameter schema on file.
Cancel a running local action. Local mode only.
No parameter schema on file.
Create an AI task plan from natural language. The plan breaks your request into
No parameter schema on file.
Execute a previously created task plan. Cloud mode only. Unavailable in remote-agent-only mode (requires THINKRUN_API_KEY).
No parameter schema on file.
Check the status of a task plan execution. Cloud mode only. Unavailable in remote-agent-only mode (requires THINKRUN_API_KEY).
No parameter schema on file.
Accessibility/DOM snapshot of the approved session tab.
No parameter schema on file.
Extract text/HTML/attributes from the approved tab.
No parameter schema on file.
Click an element in the approved tab.
No parameter schema on file.
Fill a form field (non-sensitive) in the approved tab.
No parameter schema on file.
Append text to an editable element in the approved tab, or replace its content with clear=true, with an optional per-character delay.
No parameter schema on file.
Wait for text to appear in the approved tab.
No parameter schema on file.
Capture a screenshot of the approved tab.
No parameter schema on file.
Navigate the approved tab to a URL (subject to sensitive-domain policy).
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 ThinkRun 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 93 / 100
Release 0.3.14 · 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 score93
Findings1 threat · 8 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest84178b6043637a338500031405daa278e28607f21902116f696984daabfbdc8c
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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 (67 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>".
1 of the 67 recovered tools are registered only when clientRef && onSetMode holds (dist/src/server.js:971) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 66.
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. high is the level these add up to.
66 tools are registered unconditionally · 1 more only when clientRef && onSetMode holds (dist/src/server.js:971) — typically when a key or option is configured. All 67 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| agent_identity | no tags | |
| browser_request_control | no tags | |
| browser_grant_status | no tags | |
| browser_release_control | no tags | |
| browser_snapshot | no tags | |
| browser_extract | no tags | |
| browser_click | no tags | |
| browser_fill | no tags | |
| browser_type_text | no tags | |
| browser_wait_for_text | no tags | |
| browser_screenshot | no tags | |
| browser_navigate | no tags | |
| recording_upload | no tags | |
| session_create | no tags | |
| session_status | no tags | |
| session_delete | no tags | |
| session_list | no tags | |
| session_artifacts | no tags | |
| session_wait_ready | no tags | |
| session_use | no tags | |
| set_auditing | no tags | |
| set_mode conditional | no tags | |
| page_cache_html | untrusted-input | untrusted-input: keyword "fetch", parameter "url" with "fetch" in the description |
| page_cache_text | no tags | |
| page_cache_screenshot | no tags | |
| navigate | no tags | |
| go_back | no tags | |
| go_forward | no tags | |
| wait_for_element | no tags | |
| click | no tags | |
| click_at | no tags | |
| type_text | no tags | |
| fill | no tags | |
| press_key | no tags | |
| scroll | no tags | |
| hover | no tags | |
| select_option | no tags | |
| snapshot | no tags | |
| screenshot | no tags | |
| extract | code-exec | code-exec: parameter "script" |
| evaluate | code-exec | code-exec: parameter "script" |
| tab_list | no tags | |
| tab_new | no tags | |
| tab_close | no tags | |
| tab_attach | no tags | |
| tab_switch | no tags | |
| focus | no tags | |
| window_new | no tags | |
| session_release | no tags | |
| local_diagnostics | no tags | |
| local_reset_connection | no tags | |
| get_url | no tags | |
| get_title | no tags | |
| get_html | no tags | |
| sleep | no tags | |
| get_dialog | no tags | |
| handle_dialog | no tags | |
| wait_for_text | no tags | |
| console_messages | no tags | |
| network_requests | no tags | |
| clear_logs | no tags | |
| local_action_run | no tags | |
| local_action_status | no tags | |
| local_action_cancel | no tags | |
| task_create | no tags | |
| task_execute | no tags | |
| task_status | no tags |
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 digest84178b6043637a33
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 0.3.14. Pin a release below and the command asks for exactly that one.
0.3.14
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 ThinkRun 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.