React Context MCP (uxfreak/React-Context-MCP) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 32 tools. No publisher has claimed this listing.

D
Caution
56/100

React Context MCP

Enables AI assistants to inspect React component trees, props, state, and source locations in Chrome, facilitating UI debugging and analysis.

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

⚡ Live Monitored: not connected

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

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

uxfreak

Source: Glama

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 →

Install from

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: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
// tools this server exposes32 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.

get_component_source
get_element_context
get_computed_styles
freeze_page
unfreeze_page

Resume the page after freeze_page was called.

list_pages

Get a list of pages open in the browser.

select_page

Select a page as a context for future tool calls.

close_page

Closes the page by its index. The last open page cannot be closed.

new_page

Creates a new page

navigate_page

Navigates the currently selected page to a URL.

ensure_react_attached

Ensure the React DevTools backend hook is present on the current page and list detected renderers.

list_react_roots

List React roots detected on the current page. Requires React DevTools backend to be attached.

list_components

List React component tree (limited depth) for a root. Returns generated ids usable with get_component and highlight_component.

get_component

Inspect a component by id returned from list_components. Includes props/state/source if available.

highlight_component

Highlight a component in the page using its id from list_components.

take_snapshot

Take an accessibility tree snapshot of the current page. Returns a hierarchical tree with accessible roles, names, and DOM node IDs (backendDOMNodeId) for each element. Use this to discover UI elements and get their IDs for component inspection.

get_component_map

Get a complete component map of the current page as a markdown tree. Returns only React components with their source locations in an indented tree format (e.g., "Button (src/components/Button.tsx:10:5)"). This is the primary tool for understanding React application structure at a glance.

debug_fiber_keys

[DEBUG] Test if we can find __reactFiber keys on DOM elements

debug_fiber_walk

[DEBUG] Test walking up fiber tree from DOM element to find authored component

debug_extract_metadata

[DEBUG] Test extracting proper component name and type from fiber

debug_extract_props

[DEBUG] Test extracting props with safe serialization (depth limit, circular refs)

debug_extract_source

[DEBUG] Test extracting source location from data-inspector-* props (React 19 compatible)

debug_extract_owners

[DEBUG] Test extracting owners chain by walking up fiber tree (React 19 compatible)

get_react_component_from_snapshot

Get React component information for a UI element using its accessible role and name from a snapshot. Returns component name, type, props, state, source location, and owner component chain.

get_react_component_from_backend_node_id

Get React component information for a UI element using its Chrome DevTools Protocol node ID. Faster and more deterministic than accessible name lookup. Returns component name, type, props, state, source location, and owner chain. Use backendDOMNodeId from take_snapshot.

test_aria_selector

[TEST 1] Test if Puppeteer ARIA selectors work to find "Sign up" button using aria/Name[role="button"] syntax

test_aria_to_fiber

[TEST 2] Test getting React fiber and component info from ARIA-found "Sign up" button

test_aria_edge_cases

[TEST 3] Test edge cases: element not found, trying "Log in" button

test_cdp_backend_node_id

[CDP TEST 1] Test getting backendDOMNodeId from CDP Accessibility.getFullAXTree for "Sign up" button

test_cdp_resolve_node

[CDP TEST 2] Test resolving backendDOMNodeId (53) to DOM ElementHandle using DOM.resolveNode

test_cdp_combined

[CDP TEST 3] Combined test: Get backendDOMNodeId from AX tree and immediately resolve to DOM element

test_cdp_extract_fiber

[CDP TEST 4] Extract React fiber from DOM element via Runtime.callFunctionOn

// known CVEs in dependencies3 high

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

high@modelcontextprotocol/sdk@1.21.1GHSA-345p-7cg4-v4c7

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

high@modelcontextprotocol/sdk@1.21.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.21.1GHSA-w48q-cv73-mx4w

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

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.
configTARGET_URL
// quality suggestions

Dependencies

13 dependencies, 2 flagged: puppeteer, puppeteer-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

32/32 tools missing one or more hints — get_component_source (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_element_context (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_computed_styles (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +29 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.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

No eval / new Function

4 eval() or new Function() calls — dynamic code execution

Replace eval / Function with explicit parsing or safer alternatives.

Shell command execution

9 child_process/subprocess calls in production code — runs shell commands (test-component-map.js:11, test-get-component.js:11, test-jsonrpc.js:39)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.21.1 (high), @modelcontextprotocol/sdk@1.21.1 (high)

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

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 7 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/uxfreak/react-context-mcp?variant=verified)](https://m8ven.ai/mcp/uxfreak/react-context-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 53c1a574af4be131d5d4b703e32c511f247d41c6
code hash: 386d8908d1255c37d3402f5f87c92bed4fabac7af95fbc259a5888b49fc97568
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