Revit Model MCP

Overview Schema Source Related Servers Discussions Admin

View Elements

revit_view_elements

Read-onlyIdempotent

Read one page of elements from a selected Revit view, returning IDs, category, family, type, level, and measurements. Page with offset and limit.

Instructions

Read one page of elements in a selected view.

Returns data with elements, total, offset, limit and hasMore; rows include IDs, category, family, type, level and available measurements in mm, m2 and m3. No matches or an offset beyond the result return elements=[]; advance offset while hasMore=true. Prefer revit_view_summary for counts and category discovery; use this tool for individual rows and revit_element_details for all parameters. A missing document, unknown or unsupported view, read failure or timeout raises an error; partial data is not returned.

If more than one Revit instance is running, document is required; otherwise any instance may respond. Non-empty skipped means the answer is incomplete; skippedCount includes entries beyond the first 100.

Input Schema

TableJSON Schema

Name	Required	Description
`view`	Yes	Required exact, case-sensitive non-template view name from revit_list_views, or its Revit view ID as a decimal string; no default. An exact name takes precedence over interpreting a numeric string as an ID.
`limit`	No
`offset`	No
`document`	No	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.
`categories`	No
`process_id`	No	Exact positive Revit process ID. Takes precedence over document; if both are supplied they must agree.
`timeout_seconds`	No	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.
`pickup_timeout_seconds`	No	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.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.7.0Sep 30, 2026

changedInput schema / properties / document / description

Previous value: -"Case-insensitive substring of the target active document title or file name; default null leaves requests unaddressed, so any instance may respond. Use a unique substring with multiple instances; revit_list_instances instead returns all matching instances, or all instances when omitted."New 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."

addedInput schema / properties / process_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Exact positive Revit process ID. Takes precedence over document; if both are supplied they must agree.",
+  "title": "Process Id"
+}

Changed4 schema fields changedv0.1.1Sep 15, 2026

addedInput schema / properties / document / description

Added value: +"Case-insensitive substring of the target active document title or file name; default null leaves requests unaddressed, so any instance may respond. Use a unique substring with multiple instances; revit_list_instances instead returns all matching instances, or all instances when omitted."

addedInput schema / properties / pickup_timeout_seconds / description

Added 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."

addedInput schema / properties / timeout_seconds / description

Added 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."

addedInput schema / properties / view / description

Added value: +"Required exact, case-sensitive non-template view name from revit_list_views, or its Revit view ID as a decimal string; no default. An exact name takes precedence over interpreting a numeric string as an ID."

First observedSep 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the return shape, empty-result semantics, error conditions (missing document, unknown/unsupported view, read failure, timeout), the no-partial-data guarantee, and the skipped/skippedCount incompleteness signal. This is unusually thorough behavioral disclosure.

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?

Front-loaded with the core action and return shape, then routing, then failure/skipping behavior. Every sentence carries information, though the block is dense and the trailing instance/skip paragraph could be tightened.

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

Completeness5/5

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

An output schema exists, yet the description still covers pagination, error surfaces, empty results, and incomplete-data signals for a complex 8-parameter read tool. Nothing an agent needs to call or interpret this tool is missing.

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 63%, so the schema already documents view, document, process_id, and both timeouts. The description adds offset/limit pagination semantics and the multi-instance document rule, which the schema alone doesn't convey. The categories parameter remains undocumented in both places, so it stops short of 5.

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

Purpose5/5

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

States a specific verb (read) and resource (one page of elements) scoped to a selected view. It explicitly routes to siblings: revit_view_summary for counts/category discovery, revit_element_details for all parameters. An agent can distinguish it from revit_query_elements and revit_aggregate_elements without opening any schema.

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

Usage Guidelines5/5

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

Explicit when-to-use guidance: prefer revit_view_summary for counts, this tool for individual rows, revit_element_details for full parameters. It also gives operational guidance on advancing offset while hasMore=true and clarifies the multi-instance document requirement.

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

Deploy Server