oauth-mcp-server
A production-grade Model Context Protocol (MCP) resource server with OAuth 2.1 authorization, provider-agnostic and supporting multiple MCP specification versions.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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
Shylendra
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.
get_server_statsReturns server health metrics including uptime, request count, memory usage, and the OAuth provider configuration summary.
reload_configHot-reloads the OAuth provider configuration from disk. Useful after updating scopes or provider settings.
list_server_capabilitiesLists all available tools, resources, and prompts that this server exposes, grouped by scope requirement.
search_documentsFull-text search across the mock knowledge base of 15+ articles covering Technology, Science, and Business topics.
query_analyticsQuery mock analytics data including daily active users, revenue, churn rate, and feature usage across a 30-day window.
create_documentCreates a new knowledge base article in the mock document store.
update_documentUpdates an existing knowledge base article.
list_projectsLists mock projects with optional filters for status, owner, and tag.
create_projectCreates a new project in the mock project management system.
update_projectUpdates a project's status, progress, or details.
list_filesLists files and directories in a mock file system. Use '/' to see the root, or a directory path like '/project/src' for subdirectories.
read_fileReads the contents of a mock file from the file system. Specify the full path like '/project/src/server.ts'.
upload_fileCreates or overwrites a file in the mock file system. Specify the full path and content.
echoEchoes back the text you send. Useful as a connectivity check to verify the server is reachable.
calculatePerforms a basic arithmetic operation on two numbers. Supports add, subtract, multiply, divide, power, and sqrt.
current_timeReturns the current server time in the requested IANA timezone (e.g., 'America/New_York', 'Asia/Tokyo'). Defaults to UTC.
random_numberGenerates a random integer in an inclusive range [min, max].
summarize_listComputes basic statistics (count, sum, min, max, mean, median, standard deviation) over a list of numbers.
HOSTBind address (defaults to 127.0.0.1; Cloud Run auto-sets to 0.0.0.0)K_SERVICECloud Run sets PORT (usually 8080) and automatically. The server detects K_SERVICE and binds to 0.0.0.0. Set your config path as an env var in Cloud Run:MCP_CONFIG_PATHPath to a config JSON file (defaults to config/default.json)MCP_CORS_ORIGINCORS origin for Vercel/public deploymentsMCP_DEV_TOKEN_(not set)_ A static JWT to use for local testing (bypasses real OAuth flow)MCP_LOG_BODY_LIMIT4000 Max characters logged per request/response bodyMCP_NO_AUTH$env:PORT = "6000"; $env: = "true"; npm run start:httpPORTTool 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
18/18 tools missing one or more hints — get_server_stats (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); reload_config (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_server_capabilities (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +15 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
16/18 tool handlers declare input schemas (89%)
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.
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/shylendra/oauth-mcp-server)?variant=verified to the badge 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