Revit Model MCP

Overview Schema Source Related Servers Discussions Admin

Open Documents

revit_documents

Read-onlyIdempotent

List every open document in a Revit process, including background files, and optionally include linked documents. Target the right Revit instance with process_id or document title.

Instructions

List every open document in one Revit process, including background documents. Linked documents are listed only when include_linked is set. A non-empty skipped list means the result is incomplete; skippedCount counts all skipped entries.

Input Schema

Name	Required	Description
`document`	No	Title or file name substring of the target document; needed when several Revit instances run.
`process_id`	No	Revit process ID; takes precedence over document.
`include_linked`	No
`timeout_seconds`	No	Seconds to wait for a result (default 120).
`pickup_timeout_seconds`	No	Seconds to wait for the add-in to pick up the job (default 300); unused over HTTP.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedv0.10.0Oct 14, 2026

changedInput schema / properties / document / description

Previous value: -"Case-insensitive substring of the target active document title or file name. Reads require exactly one matching instance; omitted document requires exactly one running instance. Zero or multiple matches fail before publishing. revit_list_instances returns all matching instances, or all running instances when omitted."New value: +"Title or file name substring of the target document; needed when several Revit instances run."

removedInput schema / properties / document / title
```
Removed value: -"Document"
```
removedInput schema / properties / include_linked / title
```
Removed value: -"Include Linked"
```

changedInput schema / properties / pickup_timeout_seconds / description

Previous value: -"Positive integer seconds to wait for the add-in to pick up a local or SSH job (300 when omitted); ignored over HTTP. A pickup timeout raises an error but the pending job may still execute later."New value: +"Seconds to wait for the add-in to pick up the job (default 300); unused over HTTP."

removedInput schema / properties / pickup_timeout_seconds / title
```
Removed value: -"Pickup Timeout Seconds"
```

changedInput schema / properties / process_id / description

Previous value: -"Exact positive Revit process ID. Takes precedence over document; if both are supplied they must agree."New value: +"Revit process ID; takes precedence over document."

removedInput schema / properties / process_id / title
```
Removed value: -"Process Id"
```

changedInput schema / properties / timeout_seconds / description

Previous value: -"Positive integer seconds to wait for a result after pickup (120 when omitted); HTTP uses this as its response budget. Expiry raises an error, and increasing it does not override the add-in's execution limits."New value: +"Seconds to wait for a result (default 120)."

removedInput schema / properties / timeout_seconds / title
```
Removed value: -"Timeout Seconds"
```

removedInput schema / title

Removed value: -"revit_documentsArguments"

removedOutput schema / title

Removed value: -"revit_documentsDictOutput"

Addedv0.7.0Sep 30, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, so the safety profile is covered. The description adds genuine behavioral context beyond that: background documents are included, linked documents are excluded unless include_linked is set, and the skipped/skippedCount fields signal a possibly incomplete result.

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, purpose front-loaded and no filler. The final sentence about skipped/skippedCount slightly overlaps the output schema, costing a point.

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?

With an output schema present, return values need not be described, and the tool's optional-parameter, read-only nature is well covered. The only real gap is the absence of sibling routing.

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

Parameters4/5

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

Schema coverage is 80% (baseline 3), and the description compensates for the one undocumented parameter by explaining that include_linked controls whether linked documents appear. It also frames the 'one Revit process' scoping that motivates document vs process_id selection.

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?

Opens with a specific verb+resource ('List every open document in one Revit process') and adds scope detail ('including background documents') that separates it from single-document tools like revit_document_info. It does not explicitly name which sibling to prefer, so it stops short of a 5.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance, and no alternative is named despite close siblings such as revit_document_info or revit_list_instances. The include_linked clause describes a parameter's effect, not when to choose this tool over another.

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

Deploy Server