filevine-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FILEVINE_PAT | Yes | Filevine Personal Access Token from Settings → Access Tokens | |
| ENCRYPTION_KEY | Yes | 64-character hex string for token encryption, generated via crypto.randomBytes(32).toString('hex') | |
| FILEVINE_REGION | No | API region (us or ca) | us |
| FILEVINE_CLIENT_ID | Yes | Filevine OAuth client ID from Settings → Client Secrets | |
| FILEVINE_CLIENT_SECRET | Yes | Filevine OAuth client secret from Settings → Client Secrets |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| authenticateA | Exchange your Filevine Personal Access Token (PAT) for an access token. Must be called once before using other Filevine tools. Requires FILEVINE_CLIENT_ID, FILEVINE_CLIENT_SECRET, and FILEVINE_PAT in .env |
| auth-statusA | Check whether the server is authenticated with Filevine and when the token expires. |
| logoutA | Remove the stored Filevine tokens from disk. |
| list-casesA | List cases (projects) from Filevine, optionally filtered by status or search term. |
| get-caseA | Get detailed information about a specific case (project) by ID. |
| search-contactsA | Search for contacts across all cases by name or email. |
| get-contactA | Get detailed information about a specific contact by ID. |
| list-case-contactsB | List all contacts assigned to a specific case. |
| list-notesB | List all notes for a specific case. |
| create-noteA | Create a new note on a case. Useful for logging AI summaries, findings, or follow-up items. |
| list-documentsB | List all documents for a specific case. Returns metadata, URLs, and file info — not the binary content. |
| list-tasksB | List all tasks for a specific case, optionally filtered by status. |
| create-taskA | Create a new task on a case. Note: targetDate field may be ignored by Filevine API (known issue as of Aug 2025). |
| discover-schemaA | Discover the firm's custom data structure: list all project types and their collection sections. Use this to map section selectors for get-collection tool. |
| get-collectionA | Get custom collection data (medical records, liens, settlements, etc.) for a case. Use discover-schema first to find available selectors. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| auth-status | |
| compliance-notice |
TDQS
Scored across 15 tools
Each tool targets a distinct resource and action (cases, notes, contacts, documents, tasks, collections, auth). The few overlapping areas like list-case-contacts and search-contacts are clearly differentiated by scope, and descriptions leave no ambiguity.
Most tools follow a verb_noun pattern with hyphens (list-*, get-*, create-*), which is consistent and predictable. However, authenticate, logout, and auth-status deviate from this pattern, breaking the uniformity slightly.
With 15 tools, the server is well-scoped for its purpose. Each tool addresses a distinct need, and the count is within the ideal range, not feeling excessive or sparse.
The tool surface covers core read workflows for cases, contacts, documents, notes, tasks, and custom data, plus note and task creation. However, there are notable gaps: no update/delete for cases, notes, or tasks, no document content retrieval, and no contact creation/update. These omissions create dead ends for workflows requiring full CRUD.