mcp-auth.json loses tokens for multiple servers — MCP servers keep requiring re-auth #42875

Activity

1. github-actions

   assigned

   kitlangton

   on Aug 16, 2026
2. github-actions commented on Aug 16, 2026

   

   github-actionsBot

   on Aug 16, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue might be a duplicate of existing issues. Please check:

   • MCP OAuth: opencode mcp auth re-registers a new dynamic client every run instead of reusing the stored registration #35625: MCP OAuth re-registers a new dynamic client every run instead of reusing stored registration — the hypothesis about opencode mcp add overwriting an entry and dropping tokens aligns closely with this issue.
   • V2: MCP OAuth login registers a new dynamic client every time #40767: V2 MCP OAuth login registers a new dynamic client every time — same root behavior in V2.
   • Remote MCP OAuth: access token is not refreshed despite refresh token being present #34582: Remote MCP OAuth: access token is not refreshed despite refresh token being present — related symptom where stored tokens are not used/preserved correctly.
3. iamwoz commented on Aug 17, 2026

   

   iamwoz

   on Aug 17, 2026

   More actions

   Same issue here — opencode 1.18.18, Linux (headless host).

   Setup

   Remote MCP server at https://mcp.fibery.io/mcp (OAuth + dynamic client registration), configured as fibery-[redacted]. It was previously named Fibery and later renamed.

   Symptoms

   • Every new opencode session drops back to needs_auth and forces a full interactive re-auth.

   • The log has ~30 occurrences over the last few days:

     level=WARN message="server unavailable" key=fibery-[redacted] type=remote status=needs_auth

   • One long-lived session stayed authenticated for ~23 hours, so the refresh flow works within a process — it's the persisted token that's lost, not the server-side refresh token.

   mcp-auth.json state

   Matches the report's signature exactly: leftover PKCE state, no tokens key.

   {
   "fibery-[redacted]": {
     "clientInfo": { "clientId": "ccfac24a-…" },
     "codeVerifier": "…",
     "oauthState": "…",
     "serverUrl": "https://mcp.fibery.io/mcp"
   },
   "Fibery": {
     "clientInfo": { "clientId": "3a61e33e-…" },
     "codeVerifier": "…",
     "oauthState": "…",
     "serverUrl": "https://mcp.fibery.io/mcp"
   }
   }

   Two things stand out:

   1. Both entries still carry codeVerifier + oauthState and have no tokens key, so opencode requires full re-auth every time.
   2. Fibery is a stale duplicate from before the rename — two different clientIds registered against the same serverUrl, which looks like the "re-registers a new dynamic client every run" path from MCP OAuth: opencode mcp auth re-registers a new dynamic client every run instead of reusing the stored registration #35625.

   Confirmed not a provider issue

   Fibery's authorization server metadata (/.well-known/oauth-authorization-server) advertises
   grant_types_supported: ["authorization_code","refresh_token"] and scopes_supported: "openid","offline"]. Exercising the token endpoint directly with grant_type=refresh_token returns a fresh access token, so the server-side refresh token is still valid — only opencode's stored copy was dropped.
4. big-andy-coates commented on Aug 19, 2026

   

   big-andy-coates

   on Aug 19, 2026

   More actions

   Hit this with the atlassian-rovo-mcp remote server (https://mcp.atlassian.com/v1/mcp/authv2) and traced it end to end — adding as a concrete data point since this issue doesn't currently mention Atlassian/Rovo.

   Symptom: despite having a 90-day refresh token (offline_access scope, rotating), the server needed a full interactive re-auth (opencode mcp auth atlassian-rovo-mcp) roughly every 8 hours — i.e. exactly the access token's lifetime, as if the refresh token were never being used at all.

   Server log (~/.local/share/opencode/log/opencode.log) shows the pattern clearly — repeated failures every 20-90 min for hours with no refresh attempt or error ever logged in between, just an immediate fall-through to needs_auth:

   level=WARN message="mcp connect failed" server=atlassian-rovo-mcp status.status=needs_auth
   level=WARN message="mcp connect failed" server=atlassian-rovo-mcp status.status=needs_auth
   ... (repeats every 20-90 min for ~12 hours)
   level=INFO message="cli starting" args=["mcp","auth","atlassian-rovo-mcp"]   <- manual re-auth required
   

   Root cause appears to be upstream in the MCP TypeScript SDK. Atlassian issues rotating refresh tokens ("https://id.atlassian.com/atl_token_type":"ROTATING_REFRESH" in the decoded JWT) — each refresh invalidates the old refresh token and issues a new one that must be persisted immediately. The SDK's own auth() helper had a bug where a provider.saveTokens() failure during that persistence step was silently swallowed and the client fell through to requesting a brand new authorization — exactly this symptom. Confirmed via the SDK's own changeset description:

   Against an authorization server that rotates refresh tokens... this loses credentials rather than merely hiding an error. The exchange has already succeeded server-side, so the old refresh token is invalidated at the moment the new one is issued; dropping the new token set leaves nothing usable on either side.

   Fixed upstream in modelcontextprotocol/typescript-sdk#2053, merged 2026-08-18 — but not yet in any published release (latest npm @modelcontextprotocol/sdk is still 1.30.0 from 2026-07-27, before the fix), and opencode itself currently pins 1.29.0 in packages/opencode/package.json, one minor behind even that.

   So right now there's no available fix at either layer for OAuth servers with rotating refresh tokens (Atlassian, Keycloak, and per the SDK changeset this is "the OAuth 2.1 default"). Once the SDK cuts a release containing #2053, opencode will also need to bump its @modelcontextprotocol/sdk dependency past 1.29.0/1.30.0 to pick it up.
5. rekram1-node commented on Sep 22, 2026

   

   rekram1-node

   on Sep 22, 2026

   Collaborator

   More actions

   V2 no longer uses mcp-auth.json. OAuth tokens, the client registration, and the refresh state for each MCP server are stored as a credential in the local database and written atomically per server, so an in-progress login for one server cannot rewrite or drop another server's tokens. Closing as resolved on V2; if tokens go missing on the current release, please open a new issue with steps to reproduce.

   ❤️React with ❤️1Reacted by Andy Coates
6. rekram1-node

   closed this as completedon Sep 22, 2026