schrute (sheeki03/schrute) is an MCP server listed on the M8ven Trust Index. It scores 48 out of 100, grade D. It declares 39 tools. No publisher has claimed this listing.

Caution

48/100

schrute

Item: schrute
Rating: 48
Author: M8ven

Universal Self-Learning Browser Agent. UI automation for the first run, API-level replay for the 100th run

→ sheeki03/schrute · listed on github_code

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

sheeki03

Source: github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Known vulnerabilities in dependencies: 1 critical, 7 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

// tools this server exposes39 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

schrute_explore

Start a browser session to explore a website

schrute_record

Start recording an action frame for skill generation

schrute_stop

Stop recording and return a pipeline job ID for background processing

schrute_pipeline_status

Get the status of a background recording pipeline job

schrute_sites

List all known sites

schrute_skills

List skills, optionally filtered by site

schrute_status

Get current session and engine status

schrute_dry_run

Preview a request for a skill without executing it

schrute_set_transform

Set or clear an output transform for a skill

schrute_export_skill

Export a skill as standalone curl, fetch, Python, or Playwright code

schrute_create_workflow

Create a read-only linear workflow skill from existing active GET/HEAD skills

schrute_confirm

Confirm or deny first-run of a newly-active skill

schrute_connect_cdp

Connect to an Electron app or existing browser via Chrome DevTools Protocol. Domains are host-only (port-agnostic).

schrute_recover_explore

Recover an explore session blocked by Cloudflare by handing off to a real local Chrome session

schrute_sessions

List all named browser sessions

schrute_close_session

Close a named browser session

schrute_switch_session

Switch active browser session for tool routing

schrute_import_cookies

Import cookies from a Netscape/Mozilla cookie file into a browser context

schrute_execute

Execute any skill by ID (cross-site)

schrute_activate

Manually activate a DRAFT or BROKEN skill (first execution still requires confirmation)

schrute_doctor

Run diagnostic checks on browser engine, config, database, etc.

schrute_export_cookies

Export cookies from a browser context

schrute_webmcp_call

Call a WebMCP tool discovered on the current site. Use schrute_status to see available tools.

schrute_search_skills

Search learned skills by keyword. Returns matching skill IDs, input guidance, and metadata. Use with schrute_execute to run a skill by ID.

schrute_revoke

Revoke permanent approval for a skill (next execution will require confirmation again)

schrute_amendments

List amendments for a skill

schrute_optimize

Run GEPA offline optimization on a broken or degraded skill

schrute_delete_skill

Permanently delete a skill and its amendments/exemplars (admin only)

schrute_list_tabs

List open tabs in a CDP-connected browser session

schrute_select_tab

Switch to a specific tab by URL or title in a CDP session

schrute_capture_recent

Capture recent network activity and generate skills from it. Requires a CDP-connected session (schrute_connect_cdp). Does not work with schrute_explore sessions.

schrute_performance_trace

Start/stop performance trace on the current browser session

schrute_test_webmcp

Test a WebMCP tool with sample inputs and validate the response

schrute_batch_execute

Execute multiple skill calls in sequence with batch confirmation

schrute_webmcp_directory

Search the local WebMCP tool directory across all known sites

schrute_api_coverage

Run discovery on a URL and report API surface coverage against learned skills

schrute_workflow_suggestions

List pending workflow suggestions for a site

schrute_accept_suggestion

Accept a workflow suggestion and create the workflow skill

Login

Authenticate and get access token

// known CVEs in dependencies1 critical7 high4 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.0.5GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

highfastify@5.2.1GHSA-jx2c-rxcm-jvmq

Fastify's Content-Type header tab character allows body validation bypass

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configAGENT_BROWSER_SOCKET_DIR

configProgramFiles

configProgramFiles(x86)

configSCHRUTE_DIRECT_TRANSPORT

configXDG_RUNTIME_DIR

// quality suggestions

Dependencies

17 runtime dependencies (9 dev), 2 flagged: playwright, playwright-core

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

39/39 tools missing one or more hints — schrute_explore (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); schrute_record (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); schrute_stop (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +36 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

27/39 tools referenced in tests (69%)

Write tests that reference each tool by name so every tool has at least one test.

No arbitrary install scripts

Has postinstall/preinstall script — runs arbitrary code on npm install

Remove postinstall/preinstall hooks unless they’re essential.

Production dependencies are patched

0 critical, 7 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Dependency freshness

1/17 production deps stale: pngjs@2023-02-20 (3.5y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/sheeki03/schrute?variant=verified)](https://m8ven.ai/mcp/sheeki03/schrute)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: af665e664681b8eee6525685cbe05c084b71db51

code hash: 4998d4b866639594f2975311644157bfa14c45c65e87b24e3d69c6791fa84574

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client