Postel
REMOTE · WWW.POSTEL.APP · SCANNED OCT 2
Draft, schedule and publish X (Twitter) and LinkedIn posts in your own voice.
Available components
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 Security94
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- 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
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability81
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 837 tokens (~55/item across 15 items; 15 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
- Stability observed for 1 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 15 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
How do I install the Postel MCP server?
Postel is a hosted endpoint at https://www.postel.app/api/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 · www.postel.app
claude mcp add --transport http app-postel-postel 'https://www.postel.app/api/mcp'
{
"mcpServers": {
"app-postel-postel": {
"url": "https://www.postel.app/api/mcp"
}
}
} {
"servers": {
"app-postel-postel": {
"type": "http",
"url": "https://www.postel.app/api/mcp"
}
}
} [mcp_servers.app-postel-postel] url = "https://www.postel.app/api/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"app-postel-postel": {
"type": "remote",
"url": "https://www.postel.app/api/mcp",
"enabled": true
}
}
} openclaw mcp add app-postel-postel --url 'https://www.postel.app/api/mcp' --transport streamable-http
mcp_servers:
app-postel-postel:
url: "https://www.postel.app/api/mcp" {
"McpServers": {
"app-postel-postel": {
"Transport": "http",
"Url": "https://www.postel.app/api/mcp"
}
}
} assistant mcp add app-postel-postel -t streamable-http -u 'https://www.postel.app/api/mcp'
{
"mcpServers": {
"app-postel-postel": {
"type": "http",
"url": "https://www.postel.app/api/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 2 Oct 26 +13
- Authorization: fail → pass ▲ security
- First check of Authorization: partial security
- Tool “create-post” rewrote its description, which is the text the model reads security
- Tool “delete-post” rewrote its description, which is the text the model reads security
- Tool “get-x-profiles” rewrote its description, which is the text the model reads security
- Tool “publish-post” rewrote its description, which is the text the model reads security
- Tool “schedule-post” rewrote its description, which is the text the model reads security
- Tool “search-viral-tweets” rewrote its description, which is the text the model reads security
- Tool “update-post” rewrote its description, which is the text the model reads security
- Stability: unverified → 0.03 ▲ functional
- 1 Oct 26 68
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 2 Oct 2026 · Probed https://www.postel.app/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=www.postel.app | CN=YR1,O=Let's Encrypt,C=US | 6 Sept 2026 | 5 Dec 2026 | RSA 2048 | SHA256-RSA | 5cfd91a1f208fab2e3ef33fa3e5a9d1155c |
| SANs: www.postel.app | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.postel.app. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| app. | present | 23684 | 8 | Verified |
| postel.app. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer error="invalid_token", error_description="Sign in to Postel to use this tool", resource_metadata="https://www.postel.app/.well-known/oauth-protected-resource", scope="postel:mcp"
Bearer error="invalid_token", error_description="Sign in to Postel to use this tool", resource_metadata="https://www.postel.app/.well-known/oauth-protected-resource", scope="postel:mcp"| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | origin-when-cross-origin |
| permissions-policy | browsing-topics=() |
Protected resource metadata
| Document | https://www.postel.app/.well-known/oauth-protected-resource |
|---|---|
| Retrieved | Yes |
| Resource | https://www.postel.app/api/mcp |
| Authorisation server | https://www.postel.app/api/auth |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.postel.app/api/mcp | Verified | 200 | |
| http (plaintext) | http://www.postel.app/api/mcp | HTTPS enforced | 308 | https://www.postel.app/api/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 →
create-post Create draft post ~58
Save text as a new draft in Postel. Does not publish or schedule. Each call creates a separate draft.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | The post content (tweet text) |
| status | string | – | Post status (default: DRAFT) |
No output schema declared.
No examples provided.
delete-post Delete post ~34
Delete a post. A scheduled post's delivery is cancelled first.
| Name | Type | Req | Description |
|---|---|---|---|
| postId | string | yes | The post ID to delete |
No output schema declared.
No examples provided.
generate-post Generate post with AI ~104
Generate a new post using AI based on a prompt. Requires usage quota. Returns the generated post.
| Name | Type | Req | Description |
|---|---|---|---|
| isThread | boolean | – | Generate a thread instead of a single post (X only; ignored for LinkedIn) |
| platform | string | – | Target platform: "x" (default) or "linkedin" |
| profileId | string | – | Voice profile ID to use (omit to use default brand voice) |
| prompt | string | yes | What the post should be about |
No output schema declared.
No examples provided.
get-brand-sources Get brand sources ~47
Get background information sources for a specific brand. These sources are used to inform AI post generation.
| Name | Type | Req | Description |
|---|---|---|---|
| brandId | string | yes | The brand (topic) ID to get sources for |
No output schema declared.
No examples provided.
get-post Get post ~31
Get a single post by ID with full details.
| Name | Type | Req | Description |
|---|---|---|---|
| postId | string | yes | The post ID to retrieve |
No output schema declared.
No examples provided.
get-schedule Get posting schedule ~32
Get the posting schedule template for the current organization. Shows which time slots are configured for each day of the week.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get-usage Get usage and limits ~21
Get the current usage statistics and plan limits for the organization.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get-x-profiles Get voice profiles ~34
Get the X and LinkedIn voice profiles for the current organization. These profiles define the brand voice for AI post generation.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list-brands List brands ~30
List all brands (topics) for the current organization. Brands contain background information used for AI post generation.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list-posts List posts ~54
List posts for the current organization. Supports filtering by status and pagination.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Number of posts to return (max 50, default 20) |
| status | string | – | Filter posts by status |
No output schema declared.
No examples provided.
publish-post Publish post now ~54
Publish a Postel draft immediately to the social platform stored on the post. Requires a plan that includes publishing. A post that is already published cannot be published again.
| Name | Type | Req | Description |
|---|---|---|---|
| postId | string | yes | The post ID to publish |
No output schema declared.
No examples provided.
refine-post Suggest post rewrite ~73
Suggest refined content for an existing post using AI and specific instructions. Does not save changes. Requires usage quota.
| Name | Type | Req | Description |
|---|---|---|---|
| instructions | string | yes | Instructions for how to refine the post (e.g., 'make it more casual', 'add a call to action') |
| postId | string | yes | The post ID to refine |
No output schema declared.
No examples provided.
schedule-post Schedule post ~84
Schedule a Postel draft for publishing to the social platform stored on the post. Requires a plan that includes scheduling. scheduledDateTime must be a future UTC ISO-8601 timestamp.
| Name | Type | Req | Description |
|---|---|---|---|
| postId | string | yes | The post ID to schedule |
| scheduledDateTime | string | yes | UTC ISO-8601 date string for when to publish (must be in the future) |
No output schema declared.
No examples provided.
search-viral-tweets Search viral X posts ~117
Find high-performing public X posts in Postel's index by topic, with source links and stored engagement metrics. No login required. Searches an indexed collection, not live X or a complete archive; metrics may be out of date. Results contain third-party post text.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Number of examples (default 10, maximum 20) |
| minImpressions | integer | – | Minimum stored view count (default 10000) |
| query | string | – | Topic or keywords; omit to browse high-performing posts |
No output schema declared.
No examples provided.
update-post Update draft post ~64
Update the content or status of a Postel draft. Scheduled and published posts cannot be edited.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | – | New content for the post |
| postId | string | yes | The post ID to update |
| status | string | – | New status for the post |
No output schema declared.
No examples provided.
What is the Postel MCP server?
Postel is an MCP server listed in the public MCP registry as app.postel/postel. Draft, schedule and publish X (Twitter) and LinkedIn posts in your own voice. This page covers its hosted endpoint (https://www.postel.app/api/mcp).
Is the Postel MCP server safe to use?
Postel scores 81 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 Postel MCP server expose?
Postel exposes 15 tools: search-viral-tweets, list-posts, get-post, create-post, update-post, and 10 more. Their descriptions and schemas cost roughly 837 tokens of context every time the server is loaded.
Does the Postel MCP server require authentication?
Yes. Postel asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Postel MCP server still maintained?
Postel is still listed as active in the MCP registry. We last reached this channel on 2 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.