Blog2Social - Social Media Publishing MCP server
io.github.Adenion/blog2social-api-mcpAdenionstreamable-httpv1.0.0Scanned
Connect AI agents to Blog2Social and automate social media content workflows via MCP.
10 tools: 1 can delete or cancel things, 4 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 10
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Blog2Social - Social Media Publishing MCP server can do
The Blog2Social - Social Media Publishing MCP server is published by the GitHub account Adenion. It has 10 tools. It can delete or cancel things (1 tool: connections.remove) and create or change data (4 tools: connections.add, posts.publish_post, posts.insights and account.overview). 5 tools only read.
10 tools bring in text other people can write (networks.list, connections.list, networks.properties and 7 more); 2 tools can send data out of your system (posts.publish_post and posts.insights).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Deletes or cancels 1Claude Code: deny
connections.removeUse this tool only when the user explicitly asks to disconnect a specific connected social media account.Reads text others writeNo findings
Why it is in this group
- The name "connections.remove" says "remove": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this tool only when the user explicitly asks to disconnect a specific connected social media account. It removes the connection identified by client_user_network_id from the authenticated Blog2Social user. This is a destructive action. After disconnection, the account cannot be used for publishing until it is connected again through connections.add.
Annotations the server declares
- title: Disconnect a connected social media account
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
Changes things 4Claude Code: ask
account.overviewUse this tool when the user asks for an account-level overview of Blog2Social API credit usage.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this tool when the user asks for an account-level overview of Blog2Social API credit usage. It returns the current credit balance and aggregated usage totals grouped by day, endpoint, and social network. The optional days parameter must be an integer between 1 and 30. If omitted, the endpoint default applies. The results describe aggregated account usage. They do not provide performance metrics or analytics for individual published social media posts. Use posts.insights for individual post performance.
Annotations the server declares
- title: Retrieve account usage overview
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
connections.addUse this tool when the user wants to connect an account on a selected social network.Reads text others writeNo findings
Why it is in this group
- The name "connections.add" says "add": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this tool when the user wants to connect an account on a selected social network. It starts OAuth authorization and returns an auth_link that the user must open and approve. It requires network_id and network_type_id obtained from networks.list. network_type_id 0 means profile, 1 means page, and 2 means group. The connection is not complete until the user finishes authorization. Pinterest also requires an active custom app assigned to the API service.
Annotations the server declares
- title: Connect a social media account
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
posts.insightsUse this tool when the user asks for performance metrics or analytics for your own published social media post.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "posts.insights" says "post": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "posts.insights" says "post": it sends or publishes something to other people.
Description, as the server wrote it Use this tool when the user asks for performance metrics or analytics for your own published social media post. It retrieves the latest available performance insights and associated credit information for the specified published post. It requires the public publish_url returned after a successful posts.publish_post operation. It works only for supported social networks and account types with tracking enabled. Available metrics depend on the social network, account type, published post, tracking availability, and data returned by the endpoint. Not all metrics are available for every post or network. Report only metrics actually returned by the server. Do not interpret missing metrics as zero or invent unavailable performance data. The request may deduct credits according to the account and network pricing. Consider the credit cost before making the request.
Annotations the server declares
- title: Retrieve own published post performance insights
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
posts.publish_postUse this tool when the user explicitly asks to publish social media content immediately.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "posts.publish_post" says "post": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "posts.publish_post" says "post": it sends or publishes something to other people.
Description, as the server wrote it Use this tool when the user explicitly asks to publish social media content immediately. It publishes the supplied b2s_posts to the connected social media account identified by client_user_network_id. This action publishes content directly and does not create a draft or schedule a post for later publication. postFormat must be: - 0 for text or link - 1 for image - 2 for video Image and video posts require mediaObjects with the matching IMAGE or VIDEO type and a publicly accessible HTTP or HTTPS URL. Check networks.properties before publishing to verify the requirements for the selected network and account type. The response can include: - publish_url for retrieving post performance insights with posts.insights - video_token for checking video publication status with videos.status Evaluate all returned error fields, including b2s_error_code. Do not automatically retry uncertain publishing operations.
Annotations the server declares
- title: Publish a post immediately
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 5Show 5 read-only tools
connections.listUse this tool to retrieve the social media accounts connected to the authenticated Blog2Social user.Reads text others writeNo findings
Why it is in this group
- The name "connections.list" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this tool to retrieve the social media accounts connected to the authenticated Blog2Social user. It returns the network, account type, display name, and client_user_network_id for each connection. Use it to identify the correct connected account before publishing or disconnecting it. It does not list networks available for connection. Use networks.list for that purpose.
Annotations the server declares
- title: List connected social media accounts
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
credits.balanceUse this tool to retrieve the current credit balance of the authenticated Blog2Social API account.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "retrieve": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this tool to retrieve the current credit balance of the authenticated Blog2Social API account. Use it when the user asks about available credits or before an action that may consume credits, such as publishing or retrieving post insights. It returns the current available credit balance. It does not provide individual post analytics, account usage statistics, or billing details. Publishing is not possible when the balance is zero.
Annotations the server declares
- title: Check available Blog2Social API credits
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
networks.listUse this tool to retrieve the social networks available to the authenticated Blog2Social API user.Reads text others writeNo findings
Why it is in this group
- The name "networks.list" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this tool to retrieve the social networks available to the authenticated Blog2Social API user. It returns network IDs and supported account types, including profiles, pages, and groups. Use it before connecting an account or when valid network IDs and account types are required. It does not list connected accounts or start authorization. Use connections.list to retrieve connected accounts and connections.add to start connecting an account.
Annotations the server declares
- title: List available social networks
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
networks.propertiesUse this tool to retrieve publishing requirements and capabilities for a specific social network and account type.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "retrieve": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this tool to retrieve publishing requirements and capabilities for a specific social network and account type. It returns available publishing formats and restrictions, such as supported media formats, video support, and character limits. Use it before publishing to check whether the requested content is supported. Requirements and capabilities vary by network and account type. This tool does not publish content or guarantee acceptance by the social network.
Annotations the server declares
- title: Get social network publishing requirements
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
videos.statusUse this tool after a video post has been submitted through posts.publish_post and the response contains a video_token.Reads text others writeNo findings
Why it is in this group
- The name "videos.status" says "status": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it Use this tool after a video post has been submitted through posts.publish_post and the response contains a video_token. It checks whether video publication has finished and returns the status for each target account. Possible statuses: - pending - failed - successful The response may include a publish_url after successful publication. Use the video_token returned by posts.publish_post. If the status is pending, check again later. Do not retrieve post insights until successful publication has been confirmed and a publish_url is available.
Annotations the server declares
- title: Check video publishing status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write10
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:56 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.blog2social.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://api.blog2social.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (1 destructive, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.blog2social.com/mcp: tools/list returned 10 tools to an anonymous client, including connections.remove (destructive), connections.add (write), posts.publish_post (write), posts.insights (write), account.overview (write)
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 4 to 5
- Oct 29, 2026
- Tools that change things, listed without credentials: 3 to 4
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:posts.insightsChanges thingstitledescriptionannotations
PostureRemote posture changed. Tools that change things, listed without credentials: 4 -> 5.View diff
- Tools that change things, listed without credentials: 4 to 5
Tools2 added, 1 removed, 8 changed.+2 added−1 removed~8 changedView diff
- Added:posts.insightsChanges things
- Added:posts.publish_postChanges things
- Removed:posts.create
- Changed:account.overviewChanges thingstitledescriptionannotations
- Changed:connections.addChanges thingstitledescriptionannotations
- Changed:connections.listOnly readstitledescriptionannotations
- Changed:connections.removeDeletes or cancelstitledescriptionannotations
- Changed:credits.balanceOnly readstitledescriptionannotations
- Changed:networks.listOnly readstitledescriptionannotations
- Changed:networks.propertiesOnly readstitledescriptionannotations
- Changed:videos.statusOnly readstitledescriptionannotations
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
- Tools that change things, listed without credentials: 3 to 4
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http blog2social-api https://api.blog2social.com/mcpclaude mcp add --transport http blog2social-api https://api.blog2social.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__blog2social-api__networks_list",
"mcp__blog2social-api__connections_list",
"mcp__blog2social-api__networks_properties",
"mcp__blog2social-api__videos_status",
"mcp__blog2social-api__credits_balance"
],
"ask": [
"mcp__blog2social-api__connections_add",
"mcp__blog2social-api__posts_publish_post",
"mcp__blog2social-api__posts_insights",
"mcp__blog2social-api__account_overview"
],
"deny": [
"mcp__blog2social-api__connections_remove"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as blog2social-api. Review it before you use it.
Capability tags behind 10 rules
- mcp__blog2social-api__networks_list untrusted-input
- mcp__blog2social-api__connections_list untrusted-input
- mcp__blog2social-api__networks_properties untrusted-input
- mcp__blog2social-api__connections_remove untrusted-input
- mcp__blog2social-api__connections_add untrusted-input
- mcp__blog2social-api__posts_publish_post untrusted-input, outbound
- mcp__blog2social-api__posts_insights untrusted-input, outbound
- mcp__blog2social-api__videos_status untrusted-input
- mcp__blog2social-api__credits_balance untrusted-input
- mcp__blog2social-api__account_overview untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Adenion/blog2social-api-mcp/verify?hash=bc594de5fdc2958d9208d0ceabb8918a726baad61bf959f856c6f1b2a2b4fde3" | jq -e '.changed == false'Pinned hash bc594de5fdc2, from Nov 15, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Adenion/blog2social-api-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Adenion/blog2social-api-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:14 UTC.
Blog2Social - Social Media Publishing MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Blog2Social - Social Media Publishing MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Blog2Social - Social Media Publishing MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: connections.remove.
Can the Blog2Social - Social Media Publishing MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Blog2Social - Social Media Publishing MCP server have?
- 10 tools: 1 destructive, 4 write, 5 read. connections.remove, connections.add, posts.publish_post, posts.insights, account.overview, networks.list, connections.list, networks.properties and 2 more.
Does the Blog2Social - Social Media Publishing MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Blog2Social - Social Media Publishing MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): posts.publish_post and posts.insights.
Has the Blog2Social - Social Media Publishing MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.