Repository navigation
Description
Before submitting
- Searched existing issues and discussions; no duplicate of the cross-server read-only downgrade was found.
- Included observed behavior, source references, and a reproduction against installed functions.
Area
apps/server (Claude MCP Apps adapter), visible in web/desktop app confirmations.
Problem
A deny rule for one MCP server causes T3's Claude adapter to remove the read-only hint from another server's MCP App tools. Native Datadog graphs then repeatedly show Allow datadog to run _dd_guc?, including in a Full access thread. Approving a call does not authorize the next one.
Datadog's live tools/list correctly supplies annotations.readOnlyHint: true for _dd_guc, _dd_gff, and _dd_wfd. The problem is the host's normalization, not missing annotations from Datadog.
Steps to reproduce
-
Configure a Claude project with an unrelated MCP deny rule, for example:
{ "permissions": { "deny": ["mcp__buildkite__create_build"] } } -
Connect Datadog's MCP server, or another server exposing an MCP App whose background tools are annotated read-only. The unrelated server need not be the app's server.
-
Use a Claude thread in Full access mode and generate a native Datadog graph.
-
Let the card load or reload. Its read-only helper call triggers the confirmation dialog.
Expected behavior
An unrelated Buildkite rule should not downgrade Datadog's read-only tools. Correctly annotated read-only graph calls should retain their normal prompt-free behavior. Rules that actually cover the requested server/tool must still be enforced. Removing project safety rules or disabling native graphs is not an acceptable fix.
Actual behavior and evidence
In claudeRulesMayCoverMcpTools, any active ask/deny rule whose tool name starts with mcp__ can match every server. claudeMcpToolForApps then removes the app tool's read-only hint. McpAppFrame confirms every call for which info.value.readOnly is false.
I extracted claudeRulesMayCoverMcpTools and claudeMcpToolForApps unchanged from the installed desktop bundle and invoked them with:
const tool = { name: "_dd_guc", annotations: { readOnly: true } };
const unrelated = [{ behavior: "deny", rule: "mcp__buildkite__create_build" }];
const withoutRules = claudeMcpToolForApps(tool, []).annotations.readOnlyHint;
const withUnrelatedDeny = claudeMcpToolForApps(tool, unrelated).annotations.readOnlyHint;
console.log({ withoutRules, withUnrelatedDeny });
// { withoutRules: true, withUnrelatedDeny: undefined }- Adapter rule check and hint conversion in the shipped commit.
- Desktop/web confirmation path.
- The same broad rule check is still present on main at
32a0531748c44b25072d7495ce0b9bd7e9450a87, checked 2026-11-06.
The native dialog was observed during real Datadog graph usage. Live tool discovery and the extracted-function reproduction were verified. A fresh-project UI A/B run with and without the rule has not been performed, so that end-to-end control is not claimed.
Impact
Major degradation: background graph loading produces repeated blocking permission dialogs despite read-only annotations and Full access mode.
Version and environment
- T3 Code Nightly
0.1.8-nightly.20261106.4275, macOS arm64 desktop. - Claude provider, Full access thread.
- The rule check arrived with Claude MCP Apps support in feat(server): render MCP Apps from Claude tool calls #29803 (merged November 4). The November 4
.4151source lacks it; November 6.4247,.4262, and.4275contain it. Local app logs show updates/restarts overnight and this morning. This supports the regression timing, but the previous desktop build was not run for comparison.
Settings and workaround
The app confirmation path does not consult thread permission mode or remembered per-server grants. No applicable MCP App approval setting was found in the shipped settings schema. A Codex MCP approval override does not affect this Claude app path.
Filtering out the native graph tools prevents cards from being generated, but removes wanted functionality, so that workaround was reverted. Native graphs remain enabled.
Related, distinct request
Discussion #32084 proposes inline/batched approvals and remembered grants for app tools that need approval. This report concerns read-only hints incorrectly stripped by an unrelated server's permission rules, independently of that UX proposal.
Activity
jeanpierre121 commentedon Nov 14, 2026
Same bug on stable 0.1.9 (macOS, Claude provider, Full access thread), this time with Superhuman Mail's draft card. The card calls
get_draft_send_statusand each call opens "Allow superhuman-mail to run get_draft_send_status?". My Claude settings have 13 deny rules, all for other servers (Grain, Granola, Gmail, Notion, Attio) and none for superhuman-mail.One thing the report above doesn't cover: Confirm doesn't help, because the server refuses the call after I approve it, so the card retries and the dialog comes back. My
server.trace.ndjsonfrom 13 Nov has 24ClaudeAdapterV2.callMcpToolspans for this tool and all 24 failed with:#32230 looks like it fixes my case. For the paths that keep the conservative guard (older CLIs, tools without a read-only annotation), the client still asks me to approve a call the server will always refuse - could
toolInforeport those as not callable so the dialog is skipped?I haven't run the PR, and I haven't checked if Superhuman annotates this tool as read-only.
andywillis101 commentedon Nov 14, 2026
Another case of this, with the GitHub MCP server (remote,
api.githubcopilot.com/mcp/) on Claude threads.What happens. After the agent calls
update_pull_request, T3 renders the server'spr-editview. The view loads the PR withcallTool("pull_request_read", { method: "get", owner, repo, pullNumber })(source). T3 shows "Allow github to run pull_request_read?" with only Cancel and Confirm, on every PR edit, in a thread with bypass permissions. Confirm doesn't help: the server-side call is then refused with "A Claude deny rule may cover pull_request_read, so it was not called." The view stays empty either way.Why. My project settings have two
mcp__ask rules and sevenmcp__deny rules, all for writes:mcp__github__merge_pull_request,mcp__github__merge_*mcp__github__push_files,mcp__github__push_*,mcp__github__create_or_update_file,mcp__github__delete_file,mcp__github__delete_*,mcp__github__create_branch,mcp__github__update_pull_request_branchmcp__github__pull_request_readis explicitly in myallowlist.claudeRulesMayCoverMcpToolstreats anymcp__ask or deny rule as covering every MCP tool. SoclaudeMcpToolForAppsdropsreadOnlyHint,McpAppFrameasks before the call, and themcp_callpath then refuses it on the deny rules. I understand the broad match is there for server aliases T3 can't list. The result is that a merge gate and a few write denies on one server block every read made by that server's views.Why #32230 won't fix this case. Its native
check_permissionspath applies only in Full Access with no ask rule that may cover the tool. My merge ask rule is the one I need to keep, so I stay on the conservative path.Suggestions:
mcp_call_check_permissions_v1, use it whenever a read-only tool's call is checked, whatever ask rules exist. If Claude's own evaluator returns "ask", show the card then. That covers aliases without guessing from rule names.allowrule for the exact tool as permission for the app's call.Until then, the only workaround I have is pressing Cancel. The agent's own
pull_request_readcalls are unaffected, so only the view is lost.ascrazy commentedon Nov 19, 2026
Additional evidence for #32185 on stable 0.1.10, with the repeated-dialog behavior described in #38950.
What happened
Switching conversations through the sidebar appears to trigger roughly 5–10 successive
Allow datadog to run _dd_gff?dialogs, then they stop. The screenshot shows{"telemetry":{"intent":"Fetch feature flags"}}. The user reports the navigation association as tentative.Environment
Triage was started from macOS T3 Code Desktop 0.1.10, connected to a Linux x64 systemd server running 0.1.10, Node 26.13.1. Recent conversations containing Datadog widgets use Claude with Full access. The exact conversation shown in the screenshot has not been identified.
Diagnosis and evidence
The project has 16 deny rules for specific Datadog write/feedback tools, including
mcp__datadog__delete_datadog_dashboard. None names_dd_gff.Running the unchanged v0.1.10
claudeRulesMayCoverMcpToolsandclaudeMcpToolForAppsfunctions with the real project deny rules and a synthetic_dd_gfftool annotatedreadOnly: trueproduces:The Claude adapter treats any active MCP deny rule as potentially covering every tool. This also affects different tools on the same server.
McpAppFrame prompts per call without consulting Full access or requiring a widget click. The global confirmation queue displays pending dialogs successively.
Between 14:20:15.102 and 14:20:33.875 UTC on November 19, immediately before the screenshot, the trace records 39 successful
McpAppRequests.toolInfospans and 39ClaudeAdapterV2.listMcpToolsspans. No app tool-execution spans appear in that interval. These counts are metadata lookups, not counts of dialogs.Two recent Claude Full access conversations contain 8 and 12 persisted Datadog app widgets. The user suspected two conversations created from Linear issues containing Datadog links; reading these conversations confirmed that their opening messages contain Linear issue context and Datadog links. The agents subsequently called Datadog tools that produced the embedded widgets. Loading multiple widgets is consistent with the observed bursts. Private issue identifiers and URLs are omitted.
Reproduction limits and workaround
The source-level permission reproduction is verified; switching conversations was not replayed in the UI. Trace spans do not identify the requested tools, and live
_dd_gffannotations were not fetched. No configuration was changed. Full access is already enabled, and removing the intended write-deny rules would weaken the user's restrictions.#32230 was closed without merging; #38962 remains open and addresses background widget calls opening dialogs. This evidence belongs on the existing report rather than a new duplicate.
Investigated by GPT-6 Astra through the Codex harness in T3 Code.
andreaseger commentedon Nov 19, 2026
Still reproducing on
0.1.11-nightly.20261117.4825(macOS desktop, Claude provider, Claude Code CLI 2.1.328). Two details aren't covered above.Only
askrules, all on a different server. The project has no deny rules. Its only MCP rules are exact-toolaskrules for write tools on another server, such asmcp__atlassian__createJiraIssueandmcp__atlassian__editJiraIssue, with no wildcards. User-level settings have no MCP rules. That alone is enough forclaudeRulesMayCoverMcpTools(rules, ["ask", "deny"])to strip the read-only hint from every Datadog graph helper. The title says deny rules, but an unrelated ask rule triggers it too.Live annotations confirmed. I sent control requests directly to the Claude CLI T3 launches, from the same project directory:
mcp_statusreports Datadog's graph helpers as read-only app tools:list_permission_rulesreturns noerrors, so the rules are readable and therules === nullfallback isn't involved. The onlyaskordenyrows starting withmcp__are the other-server ask rules above.Impact. Datadog calls that render a graph card are followed by
Allow claude.ai Datadog to run _dd_gff?with{"telemetry":{"intent":"Fetch feature flags"}}. When several cards mount at once, up to about 10 dialogs queue up (as in #38950). No choice is remembered, so they come back on reload.#38962 would stop dialogs for calls made without a click. It wouldn't restore the read-only hint, though, so a click inside a Datadog graph would still prompt for a read-only call. The CLI advertises
mcp_call_check_permissions_v1. Asking Claude's own evaluator about the specific call, as suggested in an earlier comment, avoids guessing from rule names. It would also keep a real ask rule on an Atlassian write tool from affecting Datadog's read-only graph calls.Investigated with Claude Code (Opus 5.5) in T3 Code.