Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

sh.objekt/mcp-upload

NPM · @OBJEKT.SH/MCP-UPLOAD

Public file storage for AI agents. Upload files and get a permalink back.

0 this week 87 Trust /100

Last scanned (12 hours ago)

Scores higher than 91% of npm servers

Category Documents and Files

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency83
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to 0xLighthouse/objekt-mcp-upload). View diagnostics → Pass
  • License check failed: no license is declared. See how to fix → Fail
  • Actively maintained (last published 216 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability78
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 654 tokens (~109/item across 6 items; 6 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 5 Nov 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 3 Nov 26 0
    • Stability: 0.97 → pass security
  • 2 Nov 26 0
    • Stability: pass → 0.97 functional
  • 27 Oct 26 0
    • Stability: 0.97 → pass security
  • 26 Oct 26 0
    • Stability: pass → 0.97 functional
  • 24 Oct 26 −5
    • CVE-2023-54404 affects this package: high ▼ security
    • Known CVEs: pass → fail ▼ security
  • 20 Oct 26 0
    • Stability: 0.97 → pass security
  • 19 Oct 26 0
    • Stability: pass → 0.97 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 6 Nov 2026 · Analysed npm/@objekt.sh/mcp-upload@0.1.5

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo 0xLighthouse/objekt-mcp-upload
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/0xLighthouse/objekt-mcp-upload/.github/workflows/publish.yml@refs/tags/mcp@0.1.5
Rekor log index 1229118183
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:5625dc4ad31326a27a796fe200cb8057ca7715574ca46496ddf1988061baa6a037cd65c5c8c3b9bae71cd61fde112c7d405ed3dc2c378126526a54d28

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 93 packages
Packages resolved 93
Stale 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~488 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_connection ~53

Test connectivity to api.objekt.sh. Use this to diagnose sandbox egress issues. If it fails, the user needs to add api.objekt.sh to their domain allowlist (Settings → Capabilities → Domain Allowlist).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_file ~45

Get a file from objekt.sh by name. Returns a link to the file without downloading the content.

NameTypeReqDescription
namestringyesFile name/key (e.g. 'photo.png')

No output schema declared.

No examples provided.

get_pricing ~19

Get current storage pricing and limits from objekt.sh.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_version ~19

Returns the installed version of the Objekt.sh MCP server.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

upload_file ~252

Upload a file to objekt.sh storage. Accepts a host file path OR base64/raw content. For files on the HOST filesystem (e.g. /Users/name/photo.png): use 'path' — reads from disk, fastest. For files you have in memory: use 'content' + 'content_type'. For files at CONTAINER paths (e.g. /mnt/user-data/): use the upload_from_sandbox tool instead.

NameTypeReqDescription
contentstring–File content — base64-encoded for binaries, raw UTF-8 for text. Use this when the file path is not accessible from the host filesystem.
content_typestring–MIME type (required with content, e.g. 'image/png'). Auto-detected when using path.
encodingstring–Content encoding. Default 'base64'. Use 'raw' for text types like SVG, HTML, CSS, JSON.
namestring–Filename for the upload. Auto-detected from 'path'. Required when using 'content'.
pathstring–Absolute path to the file on the HOST filesystem (e.g. /Users/you/photo.png). Do NOT use container paths like /mnt/user-data/.

No output schema declared.

No examples provided.

upload_from_sandbox ~100

Upload a file from a sandbox/container path (e.g. /mnt/user-data/, /home/claude/) that the host cannot access. Reads the file and uploads it directly — single tool call, no shell commands needed.

NameTypeReqDescription
namestring–Custom name for the uploaded file. Defaults to the filename.
sandbox_pathstringyesPath to the file inside the sandbox (e.g. /mnt/user-data/uploads/photo.png)

No output schema declared.

No examples provided.

Install

How do I install the sh.objekt/mcp-upload server?

sh.objekt/mcp-upload runs locally as an npm package, launched with npx -y @objekt.sh/mcp-upload. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @objekt.sh/mcp-upload

# add to Claude Code
claude mcp add sh-objekt-mcp-upload -- npx -y @objekt.sh/mcp-upload
Common questions

What is the sh.objekt/mcp-upload server?

sh.objekt/mcp-upload is listed in the public MCP registry as sh.objekt/mcp-upload. Public file storage for AI agents. Upload files and get a permalink back. This page covers its npm package (@objekt.sh/mcp-upload).

Is the sh.objekt/mcp-upload server safe to use?

sh.objekt/mcp-upload scores 87 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 6 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the sh.objekt/mcp-upload server expose?

sh.objekt/mcp-upload exposes 6 tools: upload_file, upload_from_sandbox, get_file, get_pricing, check_connection, get_version. Their descriptions and schemas cost roughly 488 tokens of context every time the server is loaded.

Is the sh.objekt/mcp-upload server still maintained?

sh.objekt/mcp-upload is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the sh.objekt/mcp-upload server?

VerifyMCP ran 15 checks on sh.objekt/mcp-upload, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about sh.objekt/mcp-upload: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.