Install Jentic One Beta

Connect the FileRun API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the FileRun API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Ffilerun.com%2Ffilerun" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Ffilerun.com%2Ffilerun" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with FileRun API.

Browse and search files and folders in a FileRun drive

Upload files to and download files from the drive

Create folders and organize files by moving or renaming them

Share files or mint web links, and revoke that access

Star files and read file metadata and thumbnails

GET STARTED

Start building with FileRun API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use FileRun API for, with concrete tasks.

★ Agent File Management via Jentic

AI agents manage files on a FileRun instance through Jentic without holding the OAuth token in context. An agent searches by intent, receives the matching operation schema, and browses, uploads, or shares files end to end. Jentic injects the bearer token at execution time, so the agent never sees the secret while it works with the drive.

Search Jentic for 'upload a file to FileRun', load the PUT /api.php/Drive/files/upload schema, and upload with Jentic-managed credentials

Automated Document Organization

An agent keeps a shared drive tidy: it searches for files matching a pattern, creates folders for each project, and moves or renames items into place. Because FileRun exposes explicit browse, search, move, and rename operations, the agent can reorganize a large drive without a human dragging files around.

Call POST /api.php/Drive/files/search to find files, then POST /api.php/Drive/files/move to place them into folders

Programmatic File Sharing

An agent shares a finished document by sharing it with a user or minting a web link, then revokes that access once the recipient no longer needs it. FileRun's share, weblink, and unshare operations let the agent control access to a file over its whole lifecycle.

Call POST /api.php/Drive/files/share to grant access, then POST /api.php/Drive/files/weblink to create a shareable link

Key Endpoints

24 endpoints — the filerun api gives ai agents programmatic file management on a self-hosted filerun instance.

METHOD

PATH

DESCRIPTION

GET

/api.php/Drive/files/browse

List files and folders in the drive

POST

/api.php/Drive/files/search

Search files and folders

PUT

/api.php/Drive/files/upload

Upload a file

GET

/api.php/Drive/files/download

Download a file

POST

/api.php/Drive/files/createfolder

Create a folder

POST

/api.php/Drive/files/share

Share a file or folder

POST

/api.php/Drive/files/delete

Delete a file or folder

GET

/api.php/Drive/files/browse

List files and folders in the drive

POST

/api.php/Drive/files/search

Search files and folders

PUT

/api.php/Drive/files/upload

Upload a file

GET

/api.php/Drive/files/download

Download a file

POST

/api.php/Drive/files/createfolder

Create a folder

POST

/api.php/Drive/files/share

Share a file or folder

POST

/api.php/Drive/files/delete

Delete a file or folder

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the FileRun API by hand means running the OAuth 2.0 flow to get a bearer token, refreshing it, and sequencing the Drive file calls against your instance host yourself. Through Jentic you install once, import the FileRun API from the API Directory, store the credential, and your agent calls it.

Permission scoping

You choose which FileRun operations your agent may call, so a rule can allow browsing, search, and download while withholding delete, move, and user administration. Scoping is by operation, so destructive calls stay out unless you grant them.

Credential isolation

Your FileRun OAuth token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'upload a file' or 'share a folder', and Jentic returns the matching FileRun operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using FileRun API through Jentic.

What authentication does the FileRun API use?

The FileRun API uses OAuth 2.0: obtain an access token through the authorization code flow or the resource owner password flow, then send it as a bearer token in the Authorization header, per its OpenAPI spec. Through Jentic, the token is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.

Can I upload and share files with the FileRun API?

Yes. Upload a file with PUT /api.php/Drive/files/upload, browse the drive with GET /api.php/Drive/files/browse, and share an item with POST /api.php/Drive/files/share.

What are the rate limits for the FileRun API?

The OpenAPI spec does not specify rate limits; check the FileRun documentation for current limits. Through Jentic, requests run from your own instance, so you control the pacing of the agent's calls.

How do I upload a file with the FileRun API through Jentic?

Search Jentic for 'upload a file to FileRun', load the returned PUT /api.php/Drive/files/upload operation with its input schema, and your agent uploads with credentials injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Is there a FileRun MCP server?

You don't need an MCP server to give your agent the FileRun API. Jentic connects it directly from the API Directory: import it, store your token, and your agent calls it, discovering operations on demand instead of loading a separate server's tool definitions into its context.

Can I limit what my agent is allowed to do with the FileRun API?

Yes. You choose which FileRun operations your agent may call, so you can allow browsing, searching, and downloading while withholding delete, move, and user-administration operations. The agent runs only the endpoints you approve, so anything destructive is excluded until you add it.

FileRun API

AI ReadinessFoundational (D)44/100

See full scorecard

Community OpenAPI document · agent-readyStorageDocument Managementoauth2, bearer24 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Browse, upload, download, organize, and share files on a self-hosted FileRun instance. Authenticates with an OAuth 2.0 bearer token.

Use for: I want to upload a file to my FileRun drive, Search for a file by name in FileRun, Download a file from a folder, Create a folder to organize project files

Not supported: Does not run the FileRun server or handle storage provisioning. Use for file, sharing, and account operations on an existing instance only.

The FileRun API gives AI agents programmatic file management on a self-hosted FileRun instance. Agents browse and search a drive, upload and download files, and organize them by creating folders and moving, renaming, or deleting items. They can share files, mint or revoke web links, star items, and read file metadata and thumbnails. Administrators can also manage user accounts on the instance. Access uses OAuth 2.0 bearer tokens, while the token endpoints themselves stay open.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

91%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: CSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

26%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4

35%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

49%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: DSignals: 1

45%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

74%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the FileRun API to your agent

Capabilities

Start building with FileRun API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

FileRun API

Jentic AI Readiness Score

FileRun API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness