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.

online.fileshareforagents/mcp

NPM · FILESHAREFORAGENTS-MCP

Storage for AI agents: free public items, or private items paid with credits or USDC (x402).

−4 this week 74 Trust /100

Last scanned (14 hours ago)

Scores higher than 49% 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 112 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability80
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1504 tokens (~94/item across 16 items; 16 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
  • Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 87% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "revoke_links" implies "revoke" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 17 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 (16)

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

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 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

  • 3 Nov 26 −5
    • Stability: pass → 0.63 functional
  • 25 Oct 26 +1
    • Stability: 0.97 → pass security
  • 24 Oct 26 −6
    • CVE-2023-54404 affects this package: high ▼ security
    • Known CVEs: pass → fail ▼ security
    • Stability: pass → 0.97 functional
  • 18 Oct 26 0
    • Stability: 0.97 → pass security
  • 17 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Oct 26 +43
    • Injection markers: unverified → pass ▲ security
    • Tool coverage: unverified → 100 ▲ functional
    • Stability: unverified → 0.90 ▲ functional
    • MCP protocol: unverified → pass ▲ functional
  • 13 Oct 26 0
    • Security disclosure: unverified → fail ▼ 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 5 Nov 2026 · Analysed npm/fileshareforagents-mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

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 112 packages
Packages resolved 112
Stale 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 16 exposed · ~1,340 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
account ~37

The account behind FILESHARE_API_KEY: credits left, files, storage used. Free. Says how to get a key when none is configured.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

buy_credits ~66

Buy N credits for the account behind FILESHARE_API_KEY with one USDC payment of N cents from WALLET_KEY (both must be configured). 1 credit = 1 paid call.

NameTypeReqDescription
creditsintegeryesHow many credits to buy (1 to 10000).

No output schema declared.

No examples provided.

buy_reads ~63

Add 1000 reads to an item. Costs $0.01 USDC. No secret needed, so anyone can top up an item they were given. Do this before sharing with many readers.

NameTypeReqDescription
idstringyesItem id, e.g. itm_...

No output schema declared.

No examples provided.

delete ~52

Delete the item now. Permanent, no refund. Free.

NameTypeReqDescription
idstringyesItem id, e.g. itm_...
secretstringyesThe item's secret (sk_...), returned once by store.

No output schema declared.

No examples provided.

extend ~79

Set a new expiry, ttl_days from now (1 to 365; must be later than the current expiry). Costs $0.01 USDC.

NameTypeReqDescription
idstringyesItem id, e.g. itm_...
secretstringyesThe item's secret (sk_...), returned once by store.
ttl_daysintegeryes–

No output schema declared.

No examples provided.

feedback ~74

Send feedback to the service operator: a missing feature, a bug, an abuse report about an item, or anything else. Free.

NameTypeReqDescription
item_idstring––
messagestringyes–
request_idstring–The request_id from an error, if reporting one.
typestringyes–

No output schema declared.

No examples provided.

pricing ~21

Prices, limits, allowed content types and the payment network. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

remove_password ~62

Remove the password; the public address then stops serving the item (signed share links still work). Free.

NameTypeReqDescription
idstringyesItem id, e.g. itm_...
secretstringyesThe item's secret (sk_...), returned once by store.

No output schema declared.

No examples provided.

retrieve ~102

Retrieve an item's content. Counts one read. Text and JSON are returned inline; binary content is returned base64-encoded unless save_to (a local path) is given, in which case it is written there.

NameTypeReqDescription
idstringyesItem id, e.g. itm_...
save_tostring–Local path to write the content to instead of returning it.
secretstringyesThe item's secret (sk_...), returned once by store.

No output schema declared.

No examples provided.

revoke_links ~68

Invalidate every share link issued so far for the item (new ones can still be created). The password address is unaffected. Free.

NameTypeReqDescription
idstringyesItem id, e.g. itm_...
secretstringyesThe item's secret (sk_...), returned once by store.

No output schema declared.

No examples provided.

set_password ~117

Protect the item's public address with a password (12 to 128 characters) and return that address. Anyone who opens it gets a password form (browsers) or can send the password in an x-password header (agents); each successful open counts one read. Replaces any previous password. Signed share_link URLs are not affected. Free.

NameTypeReqDescription
idstringyesItem id, e.g. itm_...
passwordstringyes–
secretstringyesThe item's secret (sk_...), returned once by store.

No output schema declared.

No examples provided.

share_link ~142

Create a signed, time-limited URL that lets anyone (a human in a browser, another agent) read the item without the secret, for expires_in seconds (clamped to the item's expiry). Each open counts one read. The URL itself is the credential: it bypasses any password, so send it only to the intended reader. Free. For a password-protected address instead, use set_password.

NameTypeReqDescription
expires_inintegeryesLink lifetime in seconds, e.g. 3600.
idstringyesItem id, e.g. itm_...
secretstringyesThe item's secret (sk_...), returned once by store.

No output schema declared.

No examples provided.

status ~65

Expiry, remaining reads, size, type and whether a password is set. Free, does not count as a read.

NameTypeReqDescription
idstringyesItem id, e.g. itm_...
secretstringyesThe item's secret (sk_...), returned once by store.

No output schema declared.

No examples provided.

store ~179

Store JSON, text or a file privately for 1 to 365 days (default 7). A paid call (one credit or $0.01 USDC) that includes 100 reads. Give exactly one of content (text/JSON), content_base64 (binary) or file_path (a local file). Returns id, a one-time secret, expiry and links. Keep the secret.

NameTypeReqDescription
contentstring–Text or JSON to store.
content_base64string–Binary content, base64-encoded.
content_typestring–MIME type. Detected from the content when omitted.
file_pathstring–Path of a local file to upload.
labelstring–A label to recognise the item later.
ttl_daysinteger–Days to keep the item (default 7).

No output schema declared.

No examples provided.

store_public ~183

Store JSON, text or a small file (up to 10 MB) as a PUBLIC item for 1 to 7 days, free, no payment or key needed. Anyone with the returned public link can open it (100 opens included), so never put secrets here. Give exactly one of content, content_base64 or file_path. Returns id, secret, expiry and links.public.

NameTypeReqDescription
contentstring–Text or JSON to store.
content_base64string–Binary content, base64-encoded.
content_typestring–MIME type. Detected from the content when omitted.
file_pathstring–Path of a local file to upload.
labelstring–A label to recognise the item later.
ttl_daysinteger–Days to keep the item (default 7, at most 7).

No output schema declared.

No examples provided.

wallet_status ~30

The paying wallet's address and USDC balance on the configured network, and how to fund it. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the online.fileshareforagents/mcp server?

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

npm · fileshareforagents-mcp

# add to Claude Code
claude mcp add online-fileshareforagents-mcp -- npx -y fileshareforagents-mcp
Common questions

What is the online.fileshareforagents/mcp server?

online.fileshareforagents/mcp is listed in the public MCP registry as online.fileshareforagents/mcp. Storage for AI agents: free public items, or private items paid with credits or USDC (x402). This page covers its npm package (fileshareforagents-mcp).

Is the online.fileshareforagents/mcp server safe to use?

online.fileshareforagents/mcp scores 74 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. 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 online.fileshareforagents/mcp server expose?

online.fileshareforagents/mcp exposes 16 tools: pricing, account, buy_credits, store_public, wallet_status, and 11 more. Their descriptions and schemas cost roughly 1,340 tokens of context every time the server is loaded.

Is the online.fileshareforagents/mcp server still maintained?

online.fileshareforagents/mcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the online.fileshareforagents/mcp server under?

online.fileshareforagents/mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the online.fileshareforagents/mcp server?

VerifyMCP ran 16 checks on online.fileshareforagents/mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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.