reliquary-tc doctor --probe checks the result.
Run the server over HTTP first (see Deployment and
Authentication), set auth.resource to the public URL clients are given
(for example https://vault.example.com/mcp), and keep the server itself bound to loopback.
What hosted clients need
Public IPv4 address
The vendor reaches the hostname over the public internet, so it must resolve publicly. Anthropic publishes its outbound range as IPv4 only (160.79.104.0/21, no IPv6 outbound range is listed), so
the hostname needs an A record. A host with only an AAAA record is unreachable from Claude.
A proxied Cloudflare hostname (which a tunnel hostname is) answers with IPv4 and IPv6 addresses; a
DNS-only record you manage yourself needs the A record added explicitly.
Publicly trusted certificate
The URL must behttps:// with a certificate from a publicly trusted CA. Gemini Enterprise states
that self-signed certificates are not supported, for public and private servers alike. A tunnel or
proxy that terminates TLS with a public CA (Cloudflare, Let’s Encrypt via Caddy or certbot) is
enough; a private CA or a Tailscale-only certificate is not, and nothing you configure on your own
machines changes what the vendor’s cloud accepts.
No cross-host redirects
Serve the MCP endpoint, the Protected Resource Metadata (PRM) document and the authorization-server metadata on the host you gave the client. Hosted clients do not follow a redirect to another host (anhttp to https bounce, an apex to www redirect, a login page on a different domain in
front of the discovery documents). A same-host redirect such as a trailing-slash rewrite is also
worth removing: some clients drop the method or body when they follow it.
Challenge and discovery documents
An unauthenticatedPOST to the MCP URL must reach the server and get 401 with
WWW-Authenticate: Bearer ... resource_metadata="<PRM URL>". That pointer is sent only when
auth.resource and an authorization server (auth.authorizationServers, or the bundled auth.as)
are both configured. The PRM document’s resource must equal the URL the client was given exactly,
and the authorization server’s metadata (/.well-known/oauth-authorization-server, or OpenID
openid-configuration) must carry an issuer equal to the URL it was fetched for. Make sure the
proxy forwards the WWW-Authenticate header and the /.well-known/ paths.
Egress allowlists
Gemini Enterprise controls egress for custom MCP servers with organization-policy constraints, not by source IP: its page lists none. When VPC Service Controls or project enforcement is on, add the domain names (not full URLs) of the MCP server URL, the authorization URL and the token URL toallowedEgressFqdns, and the custom MCP data source type to allowedDataSources. For a server on
one hostname with the bundled authorization server, that is the one host; with an external
IdP it is the server host plus the IdP’s authorization and token hosts. doctor --probe prints the
list it derived from your authorization-server metadata (allowlistDomains).
Streaming without buffering
Streamable HTTP answers aPOST with either one JSON body or a Server-Sent Events (SSE) stream. A
proxy that buffers the response holds the first events back until the stream ends or a buffer
fills, which looks like a hung tool call. Everything in front of the server (a tunnel, nginx,
Caddy, a CDN) must pass the response through as it is produced and must not time out an idle stream
sooner than the longest tool call.
Per-surface checklist
“Yes” means the requirement applies; the egress column says what the vendor documents. Rows marked not checked were not verified against vendor documentation for this page: look at the vendor’s current connector documentation before relying on them.
Sources, fetched 2026-10-10:
- Anthropic, IP addresses: outbound requests
such as MCP tool calls come from
160.79.104.0/21(IPv4); the previously published34.162.x.xaddresses are phased out. Re-read the page before allowlisting: the range is the vendor’s to change. - Google, Set up your custom MCP server data store
(page updated 2026-10-07): Streamable HTTP only, an
httpsURL, a certificate from a publicly trusted CA,allowedEgressFqdns/allowedDataSources, redirect URIhttps://vertexaisearch.cloud.google.com/oauth-redirect.
Cloudflare tunnel
cloudflared runs next to the server and dials out to Cloudflare, so nothing listens on a public
port, the certificate is Cloudflare’s (publicly trusted), and the hostname has A and AAAA records.
-
Keep the Host header stable.
httpHostHeaderdefaults to empty, which forwards the public hostname unchanged. List that hostname intransports.http.allowedHosts. If you overridehttpHostHeader(tolocalhost, say), the server sees a differentHostthan the one clients use: add what it sees toallowedHosts, and never rely on it for URLs (auth.resourceis the canonical origin and is never derived from a request). -
Pass the response through unbuffered. Do not set
disableChunkedEncoding: truefor this hostname. Cloudflare returns524when the origin sends nothing within its proxy read timeout (125 seconds by default), so a tool call that streams nothing for longer will be cut; send progress or keep calls shorter. Test withcurl -Nas shown below. -
Trusted proxy setting. cloudflared connects over loopback, and Cloudflare sets
CF-Connecting-IPto the visitor’s address:WithouttrustedProxies, every hosted client is counted as one unattributed source by the per-source limits (client metadata lookups, authorize admission, password-login failures). Full explanation: Running behind a proxy or tunnel. -
The Cloudflare IP list caveat. Behind a tunnel the TCP peer is
cloudflaredon loopback (or a docker bridge address if it runs in a container), not a Cloudflare edge address, so list that peer intrustedProxiesand nothing else. Do not paste Cloudflare’s published edge ranges intotrustedProxies: that list changes over time (Cloudflare adds ranges to cloudflare.com/ips before using them), a stale copy silently stops matching, and a range you do not control is exactly what the setting warns against. The ranges matter only if you expose the origin port directly and accept Cloudflare-proxied traffic there; then restrict the port to them at the firewall, not intrustedProxies. -
Cloudflare Access in front of the hostname breaks hosted clients: the vendor cloud cannot
complete an interactive login. Exempt the MCP,
.well-knownand OAuth paths, or authenticate with the server’s own OAuth only.
nginx
proxy_buffering offis what turns buffering off for every response on the location.X-Accel-Buffering: nois the per-response form: nginx honours that header when the upstream sends it, andproxy_ignore_headers X-Accel-Bufferingturns that off. It is not something you can add from the nginx side withadd_header(that header goes to the client, after the buffering decision), so rely onproxy_buffering offhere and do not assume the server sets the header.- Without
proxy_http_version 1.1nginx talks HTTP/1.0 to the upstream and cannot stream a chunked response; the emptyConnectionheader keeps the upstream connection alive. proxy_read_timeoutis the time between two reads, not the whole response, so a stream that keeps producing events never hits it.- Keep the
X-Forwarded-For $remote_addroverwrite shown here (not$proxy_add_x_forwarded_for) and list the proxy’s address intransports.http.trustedProxieswithforwardedHeader: x-forwarded-for. - The
httptohttpsredirect on port 80 is fine (same host); a redirect to a different domain is not.
Caddy
Host header
through unchanged. flush_interval -1 is low-latency mode: no response buffering, a flush after
every write. Caddy already flushes at once for text/event-stream responses and when the content
length is unknown, but the explicit setting removes any doubt. Its upstream read_timeout and
response_header_timeout default to no timeout, so a long-idle stream is only cut by whatever sits
in front of Caddy (do not add a short read_timeout to the transport http block). Caddy overwrites X-Forwarded-For for a client it does not trust, so
list the address its connections reach the server from in transports.http.trustedProxies (in Docker that is the Compose network’s gateway, not 127.0.0.1; see VPS) with the default
forwardedHeader: x-forwarded-for.
Check it
From a machine outside your network (not the server itself):curl -N and watch whether events print as they are produced or all at once at the end.
On the server host, reliquary-tc doctor --probe runs the same checks from inside:
Without
--probe, or when auth.resource is unset or names a loopback or private host, doctor
reports one skipped public-url check and makes no request. Each failing check names this page’s
section that fixes it. The probe only makes requests when you run doctor --probe (no tool call
can start it), never follows a redirect, and refuses to fetch any host, including the ones it
reads from the PRM and the challenge, that is not https or resolves to a loopback, private,
link-local, CGNAT or otherwise non-public address; it connects to the address it validated. The probe runs from your server’s network, so it cannot see a firewall that
only blocks the vendor’s addresses, and it does not yet test SSE buffering (that needs a token and a
streaming tool).