Premiere Pro MCP Server

Save Workflow Checkpoint

save_workflow_checkpoint

Persists Premiere Pro project and sequence checkpoint references with bounded operation receipt digests in a private bridge directory, preserving workflow state across server restarts.

Instructions

Persist version1 project/sequence checkpoint references and bounded operation receipt digests in the private bridge directory. Completed/pending/unknown/failed states survive server restart. No arguments or transcripts stored; no automatic replay or project restoration.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "checkpoint": "<checkpoint>"
    },
    "name": "save_workflow_checkpoint"
  }
}

Input Schema

Name	Required	Description
`checkpoint`	Yes	Strict checkpoint: schema_version 1, project_id, sequence_id, snapshot_revision, backup_reference/null, sequence_checkpoint_reference/null, operations[{operation_id,tool,state,receipt_digest/null}]. No other fields.
`idempotency_key`	No	Optional client-chosen key (1-128 chars of A-Z a-z 0-9 . _ : -) for this intended edit. Pass a fresh key per edit and reuse it only when retrying that same edit, for example after a client-side timeout. A repeat with the same tool, key and arguments is not run again: while the first call is running it fails with IDEMPOTENCY_IN_PROGRESS (poll get_last_operations); after it finished it returns the original outcome marked replayed. A definite failure with nothing applied (receipt outcome not_applied) may be retried with the same key. Reusing a key with different arguments fails with IDEMPOTENCY_KEY_REUSED. Scoped to this MCP session (the stdio server process, or the HTTP server process when Streamable HTTP is stateless per request) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated.
`expected_cep_target`	No	Optional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
`expected_project_path`	No	Optional absolute saved-project path. Every generated CEP command refuses before its body when the active project differs or is unsaved. UXP commands refuse this CEP-only guard; local-only tools do not inspect Premiere. Omit to keep existing behavior.

Output Schema

Name	Required	Description
`ok`	Yes	Whether the tool completed successfully.
`data`	No	Tool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it.
`tool`	Yes	The registered MCP tool name.
`error`	No	Failure detail when ok is false.
`receipt`	No	Versioned common mutation receipt; success never implies rendered verification.
`idempotency`	No	Present when idempotency_key deduplicated this call: replayed is true when the original outcome was returned instead of running again.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.30.0Nov 9, 2026

changedInput schema / properties / idempotency_key / description

Previous value: -"Optional client-chosen key (1-128 chars of A-Z a-z 0-9 . _ : -) for this intended edit. Pass a fresh key per edit and reuse it only when retrying that same edit, for example after a client-side timeout. A repeat with the same tool, key and arguments is not run again: while the first call is running it fails with IDEMPOTENCY_IN_PROGRESS (poll get_last_operations); after it finished it returns the original outcome marked replayed. A definite failure with nothing applied (receipt outcome not_applied) may be retried with the same key. Reusing a key with different arguments fails with IDEMPOTENCY_KEY_REUSED. Scoped to this MCP session (the stdio server process or one HTTP session) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated."New value: +"Optional client-chosen key (1-128 chars of A-Z a-z 0-9 . _ : -) for this intended edit. Pass a fresh key per edit and reuse it only when retrying that same edit, for example after a client-side timeout. A repeat with the same tool, key and arguments is not run again: while the first call is running it fails with IDEMPOTENCY_IN_PROGRESS (poll get_last_operations); after it finished it returns the original outcome marked replayed. A definite failure with nothing applied (receipt outcome not_applied) may be retried with the same key. Reusing a key with different arguments fails with IDEMPOTENCY_KEY_REUSED. Scoped to this MCP session (the stdio server process, or the HTTP server process when Streamable HTTP is stateless per request) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated."

Changed2 schema fields changedv1.25.0Oct 24, 2026

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "Optional client-chosen key (1-128 chars of A-Z a-z 0-9 . _ : -) for this intended edit. Pass a fresh key per edit and reuse it only when retrying that same edit, for example after a client-side timeout. A repeat with the same tool, key and arguments is not run again: while the first call is running it fails with IDEMPOTENCY_IN_PROGRESS (poll get_last_operations); after it finished it returns the original outcome marked replayed. A definite failure with nothing applied (receipt outcome not_applied) may be retried with the same key. Reusing a key with different arguments fails with IDEMPOTENCY_KEY_REUSED. Scoped to this MCP session (the stdio server process or one HTTP session) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated.",
+  "maxLength": 128,
+  "minLength": 1,
+  "pattern": "^[A-Za-z0-9._:-]+$",
+  "type": "string"
+}

addedOutput schema / properties / idempotency

Added value: +{
+  "additionalProperties": true,
+  "description": "Present when idempotency_key deduplicated this call: replayed is true when the original outcome was returned instead of running again.",
+  "type": "object"
+}

Changed1 schema field changedv1.24.1Oct 17, 2026

changedInput schema / properties / checkpoint / description

Previous value: -"Strict version1 checkpoint with project_id, sequence_id, snapshot_revision, backup_reference/null, sequence_checkpoint_reference/null, operations[{operation_id,tool,state,receipt_digest/null}]."New value: +"Strict checkpoint: schema_version 1, project_id, sequence_id, snapshot_revision, backup_reference/null, sequence_checkpoint_reference/null, operations[{operation_id,tool,state,receipt_digest/null}]. No other fields."

Addedv1.24.0Oct 12, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already set readOnlyHint=false and destructiveHint=false, and the description adds real behavioral context beyond them: state durability across server restart, where data lands (private bridge directory), and, importantly, the privacy boundary (no arguments or transcripts stored) plus the non-effect (no automatic replay or project restoration). It does not discuss failure modes, size bounds on the digests, or what happens on a duplicate save.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with zero filler, leading with what is persisted before moving to durability and then to exclusions. Jargon density ("bounded operation receipt digests", "private bridge directory") slightly impedes a first read, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write tool with four parameters including deep nesting and an output schema, the description covers the essential unknowns: durability, storage location, privacy posture, and the absence of restore/replay effects. What remains unsaid — idempotency behavior and the CEP guard's refusal conditions — is handled by the schema, so the description is adequate overall.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the nested checkpoint shape, idempotency key semantics, and CEP guard parameters are already fully documented in structured fields. The description only echoes a few of those concepts ("version1", "references", "receipt digests") without adding syntax or edge-case meaning, which is the expected baseline for full-coverage schemas.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb ("Persist") plus a concrete resource ("version1 project/sequence checkpoint references and bounded operation receipt digests") and a named storage location ("private bridge directory"). It implicitly contrasts with a read-side sibling by framing itself as the write side, but never names inspect_workflow_checkpoint, so differentiation must be inferred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the agent learns this is the persistence step for checkpoint data, and the closing clause rules out restore/replay duties. There is no explicit when-to-use condition, no mention of the inspection counterpart, and no prerequisite or sequencing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server