Model MCP

Overview Schema Source Related Servers Discussions Admin

Model Snapshot

revit_model_snapshot

Read-onlyIdempotent

Reads a schema version 1 project snapshot for batch audits and reports skipped items so you can identify incomplete results caused by closed worksets.

Instructions

Read a schema version 1 project snapshot for batch audits. Closed worksets can make the result incomplete. skipped means incomplete; skippedCount is the total skipped.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "revit_model_snapshot"
  }
}

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.
`parameter_rules`	No
`timeout_seconds`	No	Seconds to wait for a result (default 120).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.0.0Nov 3, 2026

removedInput schema / properties / pickup_timeout_seconds

Removed value: -{
-  "default": 300,
-  "description": "Seconds to wait for the add-in to pick up the job (default 300); unused over HTTP.",
-  "type": "integer"
-}

Changed14 schema fields changedv0.10.0Oct 14, 2026

removedInput schema / $defs / ParameterRule / properties / category / title
```
Removed value: -"Category"
```
removedInput schema / $defs / ParameterRule / properties / parameter / title
```
Removed value: -"Parameter"
```
removedInput schema / $defs / ParameterRule / title
```
Removed value: -"ParameterRule"
```

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 / parameter_rules / title
```
Removed value: -"Parameter Rules"
```

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_model_snapshotArguments"

removedOutput schema / title

Removed value: -"revit_model_snapshotDictOutput"

Addedv0.7.0Sep 30, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: closed worksets can silently make the result incomplete, and the skipped marker plus skippedCount signals that incompleteness. It still doesn't explain what happens on timeout or what the version-1 schema assumption implies for older models.

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 short sentences with the caveat and result-semantics front-loaded and no filler. The telegraphic wording ("skipped means incomplete") is efficient but borders on cryptic without naming the field's context.

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?

An output schema exists, so return values needn't be explained, and the description wisely spends its words on the incompleteness caveat instead. The main omission is guidance on selecting between document and process_id in multi-instance scenarios, though the schema itself covers that precedence.

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 coverage is 75% and the description adds no parameter-level meaning; notably parameter_rules is an undocumented filter array that the description never explains. With most parameters already documented in the schema, baseline 3 applies, but the undescribed rule filter is a real gap.

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?

"Read a schema version 1 project snapshot" gives a concrete verb and resource, and "for batch audits" narrows the scope. It does not, however, distinguish itself from near siblings such as revit_model_audit, revit_model_health, or revit_aggregate_elements, so an agent must infer which read path fits.

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?

The phrase "for batch audits" implies a usage context but never states when to prefer this over the audit/health/query siblings, nor any prerequisites (open document, active instance). Usage is implied rather than specified.

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

Deploy Server