MCP | Thomas Talks AI

A Claude Code call to an MCP method labelled read only fans out into a paid warehouse query, stored export, webhook, and audit-state change before an effect contract gates the call

Claude Code called a read-only MCP tool 186 times. The bill said otherwise.

An MCP method labelled read only can still start paid queries, create exports, send webhooks, and change audit state. Control the effects, not the method name.

Claude Code receives the first 100 of 8,742 records, follows every cursor against one snapshot, and produces a collection completeness receipt

Claude Code checked the first page and called the job done

An MCP tool returned 100 clean records, so Claude Code declared a migration complete. The other 8,642 records were still waiting behind a cursor.

Claude Code redacted the secret after it had already spread

Redacting Claude Code’s final answer does not remove a secret from tool logs, traces, caches, and review packets. Track sensitive data through the whole run with a propagation receipt.

A Claude Code run completes while a cleanup gate revokes a temporary cloud role, token, and MCP session before handoff

Claude Code finished. Its temporary cloud access did not

A completed Claude Code run can leave cloud roles, tokens, and MCP sessions behind. Require a cleanup receipt that proves temporary authority has gone.

A timed-out Claude Code MCP request leaves a paid remote job running while a guarded retry looks up the operation and attaches to the existing job

Claude Code timed out, retried, and paid twice

A timed-out MCP call may still be running and charging your account. Give paid tool operations a stable ID, a spend ceiling, and a retry receipt before Claude Code tries again.

A Claude Code trace with a missing MCP tool event is blocked by a completeness gate before replay and review

Make Claude Code prove its trace is complete before replay

A clean replay can be dangerously reassuring when the original trace dropped the tool call that changed production. Add sequence checks, expected-event accounting, and a completeness receipt before review.

Claude Code compacts its conversation while an external control-state checkpoint preserves authority, denied actions, pending effects, and evidence bindings

Keep Claude Code's safety state outside its context window

Context compaction can preserve the task while losing the decision that blocked a dangerous tool call. Store authority, denials, and unresolved effects in a control checkpoint outside the transcript.

Three individually valid Claude Code MCP reads are rejected because their source versions form a mixed production snapshot

Reject a Claude Code plan built from a mixed snapshot

Claude Code can read three correct facts and still build a plan for a system state that never existed. Record a coherent read set and reject evidence that crosses a consistency boundary.

A human approval becomes a single-use capability bound to one Claude Code operation, and the tool gateway rejects any replay after redemption

Treat Claude Code approval as a single-use capability

A human approval should authorize one exact Claude Code effect, not every retry that follows. Issue a single-use capability and record its redemption at the tool gateway.

An effect ledger records completed, failed, and pending MCP steps, then selects resume, compensate, or stop based on verified production state

Recover a partially completed Claude Code MCP workflow

A multi-step Claude Code run can fail after several external writes have already succeeded. Use an effect ledger to resume, compensate, or stop without repeating completed work.