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

io.github.bitsandtea/postking-mcp

NPM · POSTKING-MCP · 2 COMPONENTS · SCANNED AUG 4

PostKing MCP server for managing brands, generating posts, scheduling content, and publishing blogs.

+21 this week 54 Trust /100
Trust breakdown (6 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 →

Supply Chain Security37
  • Malware scan not yet available for this package.Unverified
  • Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability76
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 32233 tokens (~146/item across 220 items; 220 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 Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 96% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · postking-mcp

# add to Claude Code
claude mcp add bitsandtea-postking-mcp -- npx -y postking-mcp
# add to Codex CLI
codex mcp add bitsandtea-postking-mcp -- npx -y postking-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "bitsandtea-postking-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "postking-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add bitsandtea-postking-mcp --command npx --arg -y --arg postking-mcp
# ~/.hermes/config.yaml
mcp_servers:
  bitsandtea-postking-mcp:
    command: "npx"
    args: ["-y", "postking-mcp"]
// mcp.json
{
  "mcpServers": {
    "bitsandtea-postking-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "postking-mcp"
      ]
    }
  }
}
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.

  • 3 Aug 26 −3

    No change was recorded against any check on this day. Supply Chain Security went from 47 to 37. Other categories moved too: Stability & Change Management rose 4.

  • 2 Aug 26 +32
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Schema quality: unverified → good functional
    • Stability: unverified → 0.23 functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • MCP protocol: unverified → pass functional
    • Maintenance: unverified → pass functional
    • Licence: MIT functional
  • 31 Jul 26 −8
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 33

    First indexed and scored.

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 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 96 packages

96 packages in the resolved dependency tree · 96 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 220 exposed · ~31,224 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.

Tool Tokens
template_list ~193

List the brand's saved content templates. short {id,title,category}; medium adds platforms,isFavorite,bodyPreview (160 chars); full = raw. Pass category to filter (e.g. 'hook', 'cta', 'thread'). Results are ordered by isFavorite desc, then usageCount desc.

NameTypeReqDescription
brandIdstringBrand ID (defaults to active brand)
categorystringFilter templates by category (e.g. 'hook', 'cta', 'thread'). Omit for all.
detailstringVerbosity of returned item(s): "short" = id + primary label + status (cheap list scan); "medium" = key summary fields + counts (a useful glance); "full" = the complete object. Default "short". Lists…

No output schema declared.

No examples provided.

template_pick ~186

RE-RANKER: AI scores a caller-supplied list of candidate templates and picks the N best-fitting ones for a given theme or topic. This tool does NOT read stored templates server-side — the caller must supply the candidates explicitly (e.g. call template_list first, then pass the results here). Synchronous — no polling needed. Pass the templates array from template_list (full detail) as candidates. Returns { templateIds } — an ordered array of the winning template IDs.

NameTypeReqDescription
brandIdstringBrand ID (defaults to active brand)
countintegeryesHow many templates to pick (1–20).
templatesarrayyesCandidate templates to evaluate. Use template_list with detail='full' and pass the relevant fields.
themestringyesThe topic or theme the agent should optimise for (e.g. 'AI productivity tips').

No output schema declared.

No examples provided.

template_update ~146

Update an existing content template. All fields are optional — only supplied fields are changed. Use isFavorite=true/false to toggle favorite status.

NameTypeReqDescription
bodystringNew template body.
brandIdstringBrand ID (defaults to active brand)
categorystring|nullNew category label.
examplestring|nullNew example post.
isFavoritebooleanSet true to favorite, false to un-favorite.
patternstring|nullNew pattern description.
platformsarrayUpdated platform list.
templateIdstringyesID of the content template to update.
titlestringNew title.

No output schema declared.

No examples provided.

trends_list ~224

Browse top-trending posts (with deconstructions) for a niche + platform. Account/niche-scoped — NOT tied to a specific brand. Each post includes hook, template, pattern, and virality reason from the deconstruction. The crawler runs every 3 days; use days=3 (default) for the freshest batch. Supported niches: ai-saas, marketing, web3. Supported platforms: x.

NameTypeReqDescription
daysintegerLook-back window in days (1–30). Defaults to 3 (the freshest crawler batch).
limitintegerMaximum number of posts to return (1–50). Defaults to 20.
nichestringNiche to filter by. One of: ai-saas, marketing, web3. Defaults to ai-saas.
platformstringPlatform to filter by. Currently only 'x' is supported. Defaults to x.
sortstringSort order: 'engagement' = highest engagement score first (default); 'recent' = newest crawled first.

No output schema declared.

No examples provided.

update_blog_article ~163

Edit a blog article — title, content, excerpt, SEO fields, status, author, or category. Set status='published' to make it live on your PostKing blog.

NameTypeReqDescription
articleIdstringyesBlog article ID
authorIdstringAuthor ID (from list_blog_authors)
brandIdstringBrand ID (uses active brand if omitted)
categoryIdstringCategory ID (from list_blog_categories)
contentstringFull post body (HTML or markdown)
excerptstring
metaDescriptionstring
metaTitlestring
statusstring'published' makes it live on your blog
titlestring

No output schema declared.

No examples provided.

update_publication ~158

Update an existing blog publication's metadata — title, description, domain/routing config, or layout. Only the fields you pass are changed (partial update). Distinct from create_publication (which creates a new one). publicationId comes from list_publications or list_blogs.

NameTypeReqDescription
brandIdstringBrand ID (uses active brand if omitted)
descriptionstringPublication description / tagline
domainIdstringCustom domain ID to route this publication under
layoutstring
pathPrefixstring
publicationIdstringyesBlog publication ID (from list_publications or list_blogs)
routingTypestring
titlestring

No output schema declared.

No examples provided.

upload_asset ~299

Upload an asset to the brand library from a local file path or base64-encoded content. Prefer filePath for local files: the server reads and base64-encodes the file itself, avoiding truncation of large base64 strings over the tool_call boundary. fileBase64 is still supported for remote/inline use where no local path is available. For large files over the remote/HTTP transport, a single fileBase64 string can get truncated crossing the LLM→tool_call boundary — use the chunked flow instead: upload_asset_begin → upload_asset_chunk (× N) → upload_asset_finish. Provide exactly one of filePath or fileBase64. Returns the new asset ID and URL.

NameTypeReqDescription
brandIdstringBrand ID (defaults to active brand)
descriptionstring
fileBase64stringBase64-encoded file content. Use filePath instead when the file is local.
fileNamestringOriginal file name including extension, e.g. 'logo.png'. Derived from filePath if omitted.
filePathstringAbsolute path to a local file to upload. Preferred over fileBase64 for local files.
mimeTypestringMIME type of the file, e.g. 'image/png'
namestringDisplay name for the asset
tagsarrayTags to apply, e.g. ['logo', 'brand']

No output schema declared.

No examples provided.

upload_asset_abort ~38

Cancel a chunked asset upload in progress and discard any buffered chunks.

NameTypeReqDescription
uploadIdstringyesUpload ID returned by upload_asset_begin

No output schema declared.

No examples provided.

upload_asset_begin ~249

Start a chunked asset upload. Use this instead of upload_asset's fileBase64 param for large files over the remote/HTTP transport, where a single large base64 string can get truncated crossing the LLM→tool_call boundary. Flow: upload_asset_begin (once) → upload_asset_chunk (once per chunk, in order) → upload_asset_finish (once). Returns an uploadId that expires after 10 minutes of inactivity.

NameTypeReqDescription
brandIdstringBrand ID (defaults to active brand)
descriptionstring
fileNamestringyesOriginal file name including extension, e.g. 'logo.png'.
fileSizenumberRaw decoded byte length of the original file. Recommended — enables truncation/corruption detection at finish time.
mimeTypestringMIME type of the file, e.g. 'image/png'
namestringDisplay name for the asset
sha256stringSha256 hex digest of the original file's decoded bytes. Recommended — enables end-to-end integrity verification at finish time.
tagsarrayTags to apply, e.g. ['logo', 'brand']

No output schema declared.

No examples provided.

upload_asset_chunk ~94

Send one chunk of a base64-encoded file previously started with upload_asset_begin. Chunks must be sent in order, index starting at 0, with no gaps.

NameTypeReqDescription
fileBase64ChunkstringyesA slice of the full base64 string for this chunk
indexintegeryes0-based, contiguous chunk index
uploadIdstringyesUpload ID returned by upload_asset_begin

No output schema declared.

No examples provided.

upload_asset_finish ~59

Finalize a chunked asset upload: reassembles the buffered chunks, verifies integrity, and uploads the asset to the brand library. Returns the new asset ID and URL.

NameTypeReqDescription
uploadIdstringyesUpload ID returned by upload_asset_begin

No output schema declared.

No examples provided.

verify_domain ~48

Check DNS verification for a domain. Returns whether it's pointing to PostKing servers and what A record is needed if not.

NameTypeReqDescription
domainIdstringyesDomain ID to verify (from list_domains)

No output schema declared.

No examples provided.

vibe_edit_landing_page ~128

Use AI to edit a landing page based on natural-language instructions. Returns an operationId — poll with get_vibe_edit_status or get_job until status is 'completed'. Optionally limit to a specific scope ('headline' | 'cta' | 'full') or a single sectionId.

NameTypeReqDescription
instructionsstringyesNatural-language edit instructions, e.g. 'Make the CTA more urgent'
scopestringRestrict edits to a specific section type
sectionIdstringSpecific section ID to edit
slugstringyesLanding page slug

No output schema declared.

No examples provided.

view_asset ~146

View details of a single asset by ID. Supports detail param: short=id+type+name, medium=key fields, full=raw.

NameTypeReqDescription
assetIdstringyesAsset ID from list_assets
brandIdstringBrand ID (defaults to active brand)
detailstringVerbosity of returned item(s): "short" = id + primary label + status (cheap list scan); "medium" = key summary fields + counts (a useful glance); "full" = the complete object. Default "full". Lists d…

No output schema declared.

No examples provided.

view_landing_page ~154

Fetch a landing page by slug. detail='full' (default) returns full data JSONB; 'medium' returns summary + sectionKeys/sectionWordCounts; 'short' returns id/slug/name/status. Section bodies and rendered HTML appear only at full.

NameTypeReqDescription
detailstringVerbosity of returned item(s): "short" = id + primary label + status (cheap list scan); "medium" = key summary fields + counts (a useful glance); "full" = the complete object. Default "full". Lists d…
slugstringyesLanding page slug

No output schema declared.

No examples provided.

view_lp_draft ~144

View the unpublished draft of a landing page. detail='full' (default) includes full versionData; 'medium' adds sectionKeys/sectionWordCounts; 'short' is id/slug/name/status only.

NameTypeReqDescription
detailstringVerbosity of returned item(s): "short" = id + primary label + status (cheap list scan); "medium" = key summary fields + counts (a useful glance); "full" = the complete object. Default "full". Lists d…
slugstringyesLanding page slug

No output schema declared.

No examples provided.

view_lp_version ~143

View a specific LP version. detail='full' (default) returns full data; 'medium' adds sectionKeys/sectionWordCounts.

NameTypeReqDescription
detailstringVerbosity of returned item(s): "short" = id + primary label + status (cheap list scan); "medium" = key summary fields + counts (a useful glance); "full" = the complete object. Default "full". Lists d…
slugstringyesLanding page slug
versionIdintegeryesNumeric version ID from list_lp_versions

No output schema declared.

No examples provided.

view_side_page ~171

View a side page including sections and rendered HTML. detail='full' (default) includes rendered HTML and full overrides; 'medium' gives summary + overrideSectionKeys; 'short' gives id/slug/name/type/isPublished. Rendered HTML appears only at full.

NameTypeReqDescription
detailstringVerbosity of returned item(s): "short" = id + primary label + status (cheap list scan); "medium" = key summary fields + counts (a useful glance); "full" = the complete object. Default "full". Lists d…
sideKeystringyesSide page key (from list_side_pages)
slugstringyesParent landing page slug

No output schema declared.

No examples provided.

web_search ~170

Perform a live, real-time web search and get back a raw answer with sources — for questions like 'find me the top 10 places to share/index my MCP', 'what's the latest on X', or 'where can I find Y'. Distinct from search_web_images, which only returns images — this tool returns a synthesized text answer plus the sources it drew from (each with title, url, and optional description), and optionally related follow-up prompts. Results are returned as-is (unsummarized) — pass the answer and sources straight through to the user.

NameTypeReqDescription
brandIdstringBrand ID (defaults to active brand)
promptstringyesThe search query or question to answer via live web search, e.g. 'top 10 places to share/index my MCP'

No output schema declared.

No examples provided.

whoami ~29

Return the profile of the currently authenticated PostKing user (email, plan, credit balance, token source).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.