portkey-admin-mcp (CodesWhat/portkey-admin-mcp) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: we have no way to read this server ourselves. No publisher has claimed this listing.

C
Caution
74/100
2 months ago

portkey-admin-mcp

MCP server for Portkey Admin API - 116 tools for prompts, configs, analytics & more.

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 pushwhy connect →

Who stands behind it

CodesWhat

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

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
🚨
Secret credentials may flow to a network call
1 flow detected: ANTHROPIC_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
🔐
You'll be asked for 3 credentials: ANTHROPIC_API_KEY, MCP_AUTH_TOKEN, PORTKEY_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies1 low

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

lowesbuild@0.28.0GHSA-g7r4-m6w7-qqqr

esbuild allows arbitrary file read when running the development server on Windows

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.
configALLOWED_ORIGINSCORS allow-list; also used to validate the Host header (DNS-rebinding protection) when MCP_AUTH_MODE=none
🔐 secretANTHROPIC_API_KEY
configANTHROPIC_BASE_URL
configCLERK_AUDIENCE
configCLERK_ISSUER
configCLERK_JWKS_URL
configCORS_ORIGIN
configLOG_LEVEL
configMCP_AUTH_MODEPORTKEY_API_KEY=your_key =bearer MCP_AUTH_TOKEN=your_secret \
🔐 secretMCP_AUTH_TOKENyour_secret \
configMCP_EVENT_STOREoff off, memory, or redis
configMCP_EVENT_TTL_SECONDS
configMCP_HOST127.0.0.1 \
configMCP_MAX_REQUEST_SIZE
configMCP_MAX_SESSIONS100 Maximum concurrent stateful MCP sessions before new initialize requests are rejected
configMCP_PORT3000 Port
configMCP_PUBLIC_BASE_URLPublic absolute base URL to advertise from /auth/info and the status page; recommended for hosted deployments
configMCP_READY_CHECK_MODE
configMCP_REDIS_KEY_PREFIX
configMCP_REDIS_URLRedis URL for shared event store
configMCP_SESSION_MODEstateful stateful or stateless
configMCP_SESSION_TIMEOUT
configMCP_SHUTDOWN_TIMEOUT_MS
configMCP_TLS_CA_PATH
configMCP_TLS_CERT_PATHTLS cert for native HTTPS
configMCP_TLS_KEY_PATHTLS key for native HTTPS
configMCP_TOOL_DOMAINS
configMCP_TRANSPORT
configMCP_TRUST_PROXYfalse Trust proxy headers (for reverse proxies)
configPORTKEY_ALLOW_PRIVATE_BASE_URLPORTKEY_BASE_URL https://api.portkey.ai/v1 Portkey Admin API base URL. Point at a self-hosted Portkey gateway if needed. Loopback/private-network hosts are rejected unless =true
🔐 secretPORTKEY_API_KEYclaude mcp add -e =your_key portkey-admin -- npx -y portkey-admin-mcp
configPORTKEY_BASE_URLPORTKEY_ALLOW_PRIVATE_BASE_URL — Set to true to allow a on loopback or a private network (e.g. a self-hosted gateway at http://localhost:8787)
configPORTKEY_TOOL_DOMAINSTo expose only a focused subset of tools in stdio clients, set :
configRATE_LIMIT_ENABLED
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
deployREDIS_URL
// quality suggestions

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

150/150 tools missing one or more hints — get_cost_analytics (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_request_analytics (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_token_analytics (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +147 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

Only 0/150 tool handlers declare input schemas (0%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

Only 1/150 tool handlers wrap calls in try/catch (1%)

Wrap each tool handler body in try/catch and return a structured error response.

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.

Secrets stay with their owner

1 secret/sensitive value flow into network calls (ANTHROPIC_API_KEY → dynamic)

Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.

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/s-b-e-n-s-o-n-portkey-admin-mcp-4p38vi?variant=verified)](https://m8ven.ai/mcp/s-b-e-n-s-o-n-portkey-admin-mcp-4p38vi)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 893805c1f2567ee1a16d43dbfc17922ea5a4b94c
code hash: 080cea09ada1ae25890b77b75a7845411c3aef541d5e17fe4eef55b2e1454ccd
verified: 6/18/2026, 11:30:39 AM
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