DevToolkit MCP Server
Provides AI assistants with 28 developer tools across file, git, code analysis, HTTP, and system domains, enabling tasks like file editing, repository management, code analysis, and shell command execution.
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
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
tusharrayamajhi
Source: Glama
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.
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.
read_fileRead the contents of a file. Supports optional line range.
write_fileWrite content to a file, creating it if needed. Asks for confirmation if file already exists.
list_directoryList files and directories at a given path with metadata.
search_in_filesSearch for a text pattern across files using glob patterns.
get_file_infoGet metadata for a file: size, timestamps, permissions.
delete_fileDelete a file or directory. Always asks for user confirmation first.
git_statusShow the working tree status of a git repository.
git_logGet the commit history for a repository.
git_diffShow diff between commits, branches, or working tree.
git_blameShow what revision and author last modified each line of a file.
git_branchesList all local and remote branches.
git_show_commitShow details and diff for a specific commit.
analyze_complexityAnalyze code complexity: functions, classes, nesting depth, cyclomatic complexity.
find_todosFind all TODO, FIXME, HACK, NOTE, and XXX comments in files, then AI-prioritizes them by urgency.
count_linesCount total, blank, comment, and code lines in a file or directory.
detect_languageDetect the programming language of a file.
find_duplicatesFind duplicate or near-duplicate code blocks across files.
get_importsExtract all import/require statements from a source file.
http_requestMake an HTTP request. Supports GET, POST, PUT, PATCH, DELETE with custom headers and body.
fetch_jsonFetch JSON from a URL and return it formatted. Supports dot-path extraction.
check_url_statusCheck the HTTP status and response time of one or more URLs.
download_fileDownload a file from a URL and save it to a local path.
get_system_infoGet detailed system information: OS, CPU, memory, architecture, hostname.
get_envRead environment variables. Sensitive values are automatically masked.
run_commandExecute a shell command safely. Validated against an allowlist of safe tools.
list_processesList running processes with their PID, name, and resource usage.
get_disk_usageGet disk usage for a directory or the whole system.
get_network_infoGet network interfaces and their IP addresses.
run_backgroundStart a long-running process (dev servers, watchers) in the background. Captures output for a few seconds then detaches — process keeps running. Returns PID + initial output. Use for: npm run dev, uvicorn, nodemon, python manage.py runserver.
read_process_outputRead the latest buffered output from a background process started with run_background.
check_command_statusCheck if a background command (started with run_background) has finished. Returns running=true/false, exit_code, and output so far. Use in a loop: wait(15) → check_command_status(pid) → repeat until running=false.
check_portCheck if a TCP port is open/listening on localhost. Use after run_background to confirm a dev server started. Returns true if something is listening.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
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 — read_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); write_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_directory (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.
Tool inputs are validated
30/32 tool handlers declare input schemas (94%)
Declare an inputSchema with zod/joi/yup on every tool definition.
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.
Shell command execution
2 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 18 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (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.
[](https://m8ven.ai/mcp/tusharrayamajhi/devtoolkit-mcp)?variant=verified from the URL.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