Skip to main content
Glama

Pull File from Remote Machine

remote_pull

Copy a file from a remote machine and get a temporary download link, so you can open artifacts like checkpoints, images, CSV outputs, or oversized logs that won't fit in command output.

Instructions

PRO PLAN ONLY. Copy a FILE off a remote machine so you (or the user) can actually open it — a training checkpoint, a rendered image, a CSV a job produced, a log too big to print. Free and anonymous callers cannot start file transfers; tell a Free user to upgrade and an anonymous user to sign in with Pro. A plan-restricted machine also fails with reason:"plan_device_limit". USE THIS instead of cat-ing a file through remote_exec: exec output is capped at 1 MiB and mangles binary, whereas this moves the real bytes. The machine reads the file and hands it to the relay, which stores it TEMPORARILY and returns a blobId plus a download link. A blob/link created while transfer was allowed remains usable only until its existing TTL even after downgrade; do not promise renewal.

TEMPORARY MEANS TEMPORARY. The stored copy stops being readable 24 hours after it is created, whether or not anybody fetched it, and the download link stops working after ONE hour. An hourly, retrying sweep removes expired bytes afterward; an inaccessible object may remain until cleanup succeeds. The relay is a courier, not a file host: there is no way to list, rename, or keep a blob, and nothing here is a backup. If the user needs the file permanently, give them the link promptly and tell them it expires — or push the file to their own storage from a job.

LIMIT — 100 MiB per file. Anything larger is refused, and for a genuinely large artifact (a multi-GB model checkpoint) the right answer is to have the JOB copy it to the user's own storage as its last step (aws s3 cp, rclone, scp). Do not try to split a big file into chunks with this tool.

path must be ABSOLUTE (/home/u/out.ckpt, or C:\Users\u\out.ckpt on Windows) and must name a regular file — a directory is refused, so tar -czf it first with remote_exec and pull the archive. Name the machine with code exactly as the user said it — an AIC- session code (e.g. AIC-XYZ-1234) or, when authenticated with an API key, a saved alias or hostname such as 'wearfits-m3'; if the user's text contains 'aic-'/'AIC-' in any case, that is one of their machines. Tell the user the link and its expiry; do not paste file contents you have not been asked for.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYesHow the user named the machine — pass it exactly as given (AIC- session code, or a saved alias/hostname when authenticated with an API key).
pathYesABSOLUTE path of the file on the remote machine, e.g. `/home/u/aic-jobs/train/out.ckpt` or `C:\Users\u\out.png`. A relative path is refused rather than resolved against some working directory. Must be a regular file: archive a directory first (`tar -czf /tmp/out.tgz <dir>`) and pull the archive.
Behavior5/5

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

The description discloses far beyond the annotations: temporary storage with 24-hour blob TTL and 1-hour link TTL, hourly sweep behavior, `plan_device_limit` failure reason, the relay being a courier not a file host, no listing/renaming/backup support, and TTL persistence after downgrade. There is no contradiction with the annotations; readOnlyHint=false aligns with the tool creating temporary blobs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but every section earns its place: plan restrictions, behavioral caveats, limits, path rules, and machine-code handling. It is well-structured with clear paragraph breaks and front-loaded with the most decision-critical facts (purpose and plan gate). No fluff or redundant restatement of the tool name.

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?

With no output schema, the description carries the full burden of explaining the return contract, and it does: it returns a `blobId` and download link, specifies expiration, covers failure modes, size limits, and directory refusals. It also provides complete workaround guidance for large files and permanent storage needs. Nothing needed for correct invocation is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is already solid. The description still adds meaning beyond the schema: it emphasizes passing `code` exactly as the user stated, explains case-insensitive detection of AIC- session codes, reinforces that relative paths are refused, and clarifies Windows path conventions. It also ties both parameters together in practical workflow guidance (tar directories first).

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?

The description opens with a specific verb and resource: 'Copy a FILE off a remote machine so you (or the user) can actually open it.' It immediately clarifies the tool's scope (regular files, not directories) with concrete examples (checkpoint, image, CSV, log). It also distinguishes itself from sibling remote_exec by explicitly saying to use this instead of cat-ing.

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?

The description gives explicit when-to-use and when-not-to-use guidance: 'USE THIS instead of cat-ing a file through remote_exec' and explains why (1 MiB cap, binary mangling). It directs large artifacts to job-side storage (`aws s3 cp`, `rclone`, `scp`), tells users to tar directories before pulling, and specifies upgrade requirements for Free/anonymous callers. This is exemplary routing behavior.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AICommander-dev/aicommander'

If you have feedback or need assistance with the MCP directory API, please join our Discord server