MCP / API Resource-Server Hardening

    1

    Signature verification proves a token came from your issuer.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    MCP / API Resource-Server Hardening

    Example session with this skill installed

    Our MCP server verifies Keycloak JWTs and then trusts them. Review it against the hardening checklist and fix what's missing: it's multi-tenant and the realm is shared with our customer-facing apps.

    • Read your context and instructions
    • Compiled the mcp api resource-server

    Summary

    Four gaps found; all four are the defects the checklist exists for. Fixed in the store layer and the single handler, with tests that attack both transports.

    GapBeforeAfter
    Any valid realm token acceptedsignature + iss + exp onlyauthorizeClient against OIDC_ALLOWED_CLIENTS=agent-runner; customer-app tokens now 403 CLIENT_NOT_ALLOWED
    No audiencetokens for the web app replayable hereaudience: https://mcp.example.com required (RFC 8707)
    Unmapped app key fell back to tenant defaultsilent cross-tenant readtenantFor returns null, 403 TENANT_NOT_CONFIGURED; escape:../x mapping dropped at parse
    author taken from the request bodyany key holder could write as anyonederived from the credential; body value kept as claimedAuthor only

    Tests added (hardening.test.mjs pattern): 12 pass.

    • SERVER_DERIVED injection on REST and MCP: author, version, bytes, createdAt, scope all ignored or labelled
    • isolation: beta cannot read, list or see versions of alpha's scope; cross-tenant read is 404, same as never existed
    • audit: a distinctive scope name appears nowhere in 4 logged exits (write, MCP read, unauthenticated, unmapped)

    Audit line now (families only):

    {"event":"request","caller":"oidc:agent-runner","tenant":"acme","route":"/v1/context/:scope","tool":"context_write","scope":"project","status":200,"ms":3}
    

    Also added: /.well-known/oauth-protected-resource and WWW-Authenticate: Bearer resource_metadata=... on 401, so MCP clients discover the authorization server without configuration.

    Next steps

    • Register the audience with the identity provider and roll the new tokens.
    • Keep OIDC_ALLOWED_CLIENTS in configuration; it starts empty and stays explicit.
    • If a future fix makes one of these tests fail, change the test and say why; do not fix it back.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Signature verification proves a token came from your issuer. It does not prove the token was meant for your service, that the client it was issued to may use this surface, that the credential is assigned a tenant, or that the request body can be trusted for fields the server owns. Each of those gaps shipped once as a real defect; this skill is the code and the tests that keep them closed.

    token-verifier.mjs

    RS256/ES256 against the issuer's JWKS with node:crypto only; discovery or explicit JWKS URI; kid required and key type matched to the algorithm; one refetch on an unknown kid; iss, exp, nbf and audience (RFC 8707); every failure is { ok: false } with no fallback, including an unreachable JWKS.

    authorization.mjs

    Client from azp/client_id only (never username or sub); explicit allow-list where an empty list rejects everyone; tenant mapping that drops unsafe ids at parse and returns null for an unmapped credential (403 TENANT_NOT_CONFIGURED, never a default); applyServerDerived so author, version, size, timestamps and the URL scope never come from the body and a caller's value is kept only as a labelled claim; audit helpers that log scope families and route templates, describe batched JSON-RPC, and never carry names; RFC 9728 metadata and WWW-Authenticate.

    example-server.mjs

    A loopback resource server with REST and MCP Streamable HTTP surfaces applying every rule: 401 vs 403 semantics, 404 for cross-tenant reads, one audit line per request at the single handler.

    12 tests

    A fake authorization server with generated keys; every verifier failure; rotation; allow-list; fail-closed tenancy; a SERVER_DERIVED injection test on both transports; isolation for read, list and versions on REST and MCP; the negative audit test that a distinctive scope name appears nowhere.

    reference/checklist.md

    Each rule with the defect it came from, the status-code table, and the instrument-verification habits that caught false readings.

    Node 20+, no packages. Network only to the issuer's discovery and JWKS URLs you configure.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.

    Bearer tokens only; no DPoP/mTLS. Built-in scope parsing assumes family/name format. Node 20+ required.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 19 days ago

    Software
    Node.js 20+OIDC authorization server

    The authorization server needs a JWKS endpoint.

    Permissions

    Read Files
    Network Access
    Terminal / Shell
    Write Files
    Environment Variables

    Shell runs node for the tests and the example server. Read files: your server source when adapting the pattern. Write files: test and source files you add. Network: the verifier fetches the issuer's discovery document and JWKS at the URLs you configure; the example server listens on 127.0.0.1. Tests make no network calls. Configuration (issuer, allowed clients, tenant map, app keys) is read from environment variables you set for the example server.

    Listed19 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a production-ready security layer for MCP and API servers, enforcing fail-closed OIDC verification, client allow-lists, and strict tenant isolation to prevent credential leaks and cross-tenant data access.

    It is built for Node 20+ environments using native modules and is compatible with any OIDC-compliant provider like Auth0, Keycloak, or Okta, making it ideal for securing MCP servers exposed to external AI agents.

    Setup involves initializing the verifier with your OIDC issuer URL, configuring your client allow-list via environment variables, and defining your tenant mappings to ensure isolated data partitioning.

    You receive the complete implementation logic, a suite of 12 regression tests covering edge cases like cross-tenant access attempts, and documentation for RFC 9728 compliant metadata setup.

    While it excels at securing HTTP-based MCP and REST integrations, it currently only supports Bearer tokens; DPoP and mTLS binding are not included in the current version.

    Unlike generic AI-generated code, this skill includes specific guards against field injection and handles complex JWKS rotation and 'kid' validation natively, ensuring your server doesn't fail open during a key rotation.

    New in APIs & Backend