Oh My Share
REMOTE · OPENANTHROPIC.COM
Publish HTML/code from your agent to openanthropic.com and get a shareable link.
Available components
Last scanned (12 hours ago)
Scores higher than 57% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Documents and Files
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1182 tokens (~168/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management43
- Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 8 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
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
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.
- 20 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Nov 26 +1
- Stability: unverified → 0.03 ▲ functional
- 8 Nov 26 66
First indexed and scored.
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 21 Nov 2026 · Probed https://openanthropic.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=openanthropic.com | CN=WE1,O=Google Trust Services,C=US | 16 Nov 2026 | 14 Feb 2027 | ECDSA 256 | ECDSA-SHA256 | cecca447c987105d0e84e15dfbd55864 |
| SANs: openanthropic.com, lut.openanthropic.com, *.lut.openanthropic.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of openanthropic.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| openanthropic.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://openanthropic.com/mcp | Verified | 200 | |
| http (plaintext) | http://openanthropic.com/mcp | HTTPS enforced | 301 | https://openanthropic.com/mcp |
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 →
delete ~81
Permanently delete one of your own assets by id. Irreversible: the share URL stops working immediately and the content cannot be restored. Requires authentication and ownership; ids you do not own return an error. Use list_assets to find the id; there is no bulk delete.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | 12-character asset id you own (from list_assets). |
No output schema declared.
No examples provided.
get_info ~69
Return Oh My Share service metadata: version, REST and MCP endpoints, feature list, and per-IP rate limits (10 uploads/hour, 500 views/hour). Read-only, no auth, cheap to call. Use it once at startup to discover capabilities; use list_assets or search_gallery for actual content.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_assets ~75
List up to 50 assets owned by the authenticated user, newest first, with id, filename, timestamps and share URL. Requires an API key or signed-in session; read-only, and results are capped at 50 with no pagination. Use search_gallery for public works from other users, or view to open one of your assets.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
search_gallery ~176
Search public gallery works by keyword across title, description, tags and id; omit query to browse the newest works. Returns a paginated result set (items, total, page, pages) where each item has id, title, views and URLs. sort is new (newest) or hot (most liked and viewed); limit is capped at 20. No auth required. Use view to open a result, or list_assets for your own uploads.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Results per page, 1 to 20. Default 10. |
| page | integer | – | 1-based page number. Default 1. |
| query | string | – | Keyword matched against title, description, tags and id; empty returns the newest works. |
| sort | string | – | new = newest first; hot = most liked and viewed. |
No output schema declared.
No examples provided.
upload ~312
Upload one HTML/code payload and get a public share URL plus an edit token. Each call creates a new asset unless idempotencyKey is reused. Anonymous uploads are rate-limited to 10/hour and 50/day per IP; authenticated uploads are limited per account. Content is public unless password-protected and expires after expiresIn (default 7d). Use upload_site for multi-file sites, view to read back, list_assets for your own files, or delete to remove one.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | HTML or code to publish (required, max 500 KB). |
| description | string | – | Optional description for the asset. |
| expiresIn | string | – | Retention: 1h, 24h, 7d, 30d, 90d, or 0 for permanent. Default 7d. |
| filename | string | – | Optional display filename used in the title and download name (max 200 chars). |
| idempotencyKey | string | – | Optional 1-128 char retry key. Reusing it with the same payload returns the original asset; the edit token is only returned to the original caller. |
| language | string | – | Content language hint, e.g. html, css, js, json, markdown. Default html. |
| password | string | – | Optional password; the web view asks for it before showing content. |
| tags | string | – | Optional comma-separated tags. |
| title | string | – | Optional title shown in the viewer and gallery metadata. |
No output schema declared.
No examples provided.
upload_site ~239
Publish a multi-file static site from an authenticated account. Pass files as an array of {path, content} strings; the root must contain index.html or index.htm. Returns a /s/<id>/ URL that serves HTML/CSS/JS/assets. Limits: 200 files, 20 MB total, 5 MB per file. Requires OAuth or an API key; site links never show the anonymous badge. Use idempotencyKey to make retries safe.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | Optional description. |
| expiresIn | string | – | Retention: 1h, 24h, 7d, 30d, 90d, or 0 for permanent. Default 7d. |
| files | array | yes | Site files. Paths are relative and must not contain .. or absolute paths. |
| idempotencyKey | string | – | Optional 1-128 char retry key. Reusing it with the same payload returns the original site; the edit token is only returned to the original caller. |
| tags | string | – | Optional comma-separated tags. |
| title | string | – | Optional site title; defaults to "site". |
No output schema declared.
No examples provided.
view ~95
Fetch a single asset by id and return its content, filename, creation time and share URL. Read-only and safe to retry; public assets need no auth, password-protected assets return an error with the share URL, and client-encrypted content is returned as stored. Use search_gallery to find an id, or list_assets for your own uploads.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | 12-character asset id returned by upload or search_gallery. |
No output schema declared.
No examples provided.
How do I install the Oh My Share MCP server?
Oh My Share is a hosted endpoint at https://openanthropic.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · openanthropic.com
claude mcp add --transport http com-openanthropic-oh-my-share 'https://openanthropic.com/mcp'
What is the Oh My Share MCP server?
Oh My Share is an MCP server listed in the public MCP registry as com.openanthropic/oh-my-share. Publish HTML/code from your agent to openanthropic.com and get a shareable link. This page covers its hosted endpoint (https://openanthropic.com/mcp).
Is the Oh My Share MCP server safe to use?
Oh My Share scores 72 out of 100 on VerifyMCP. 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 Oh My Share MCP server expose?
Oh My Share exposes 7 tools: upload, upload_site, list_assets, view, delete, and 2 more. Their descriptions and schemas cost roughly 1,047 tokens of context every time the server is loaded.
Does the Oh My Share MCP server require authentication?
No. We connected to Oh My Share without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Oh My Share MCP server still maintained?
Oh My Share is still listed as active in the MCP registry. We last reached this channel on 21 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 Oh My Share MCP server?
VerifyMCP ran 13 checks on Oh My Share, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.