threadflow-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@threadflow-mcp draft this 4-post thread about our launch, then post it if it scores above 45"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
threadflow-mcp
Thread publishing discipline for AI agents. Draft an X/Twitter thread, get
the per-post evidence check, then enforce that ONLY a validated draft can be
scheduled or posted — with an optional pre-spend gate: when a
marketing-scope-mcp
pre-flight score is supplied, an offer scoring below 45/100 is refused with
the sibling's own verbatim kill rule.
The sibling of both — research-scope-mcp
(sources → citations) and marketing-scope-mcp (tactics → scored offers) —
extended from planning your campaign into publishing your threads.
The discipline
validate_thread → draft_thread → schedule_thread / post_thread
(evidence) (registry) (enforced gates)validate_thread(posts[])— deterministic per-post checks with evidence: 280-char platform limit, 25-post thread limit, empty/one-word posts, hook quality on post 1, and the links-on-final-post convention. Reads only; the registry is untouched.draft_thread(posts[])— validate AND register the posts. Blocking issues (too-long, empty-post, too-many-posts) refuse the draft outright.schedule_thread(posts[], run_at, preflight?)/post_thread(posts[], preflight?)— refuse any posts array that was never drafted, with an error naming the exact text. This is the thread-tool equivalent of the sibling's unscored-offer gate: no pre-flight → no publish.The kill-rule gate (the white space). Pass the marketing server's
score_offerresult aspreflight.offerand a score < 45 comes back as:GATE REFUSED — pre-flight score 38/100 (grade D) is below the kill rule: "Below 45 out of 100 — rework the offer before spending anything on traffic."Honesty boundary, stated in the tool docs too: the gate receives the score as a tool argument; it cannot cryptographically prove the sibling scorer produced it. It is only as strong as the agent chain that runs
score_offerfirst — and the exact refusal text is written so the audit trail says precisely why a post was refused.Platform boundary, stated in the tool docs too: this server holds no X credentials by design.
post_thread/schedule_threadclear and audit a draft; the authenticated platform POST happens in the ThreadFlow app's Twitter-authenticated path (SUPABASE_*edge functions), never here.
Related MCP server: ShipPost MCP
Install
Node ≥ 20.
npm install -g threadflow-mcp
# or run from source:
git clone https://github.com/AxelVerneBooks/threadflow-mcp
cd threadflow-mcp && npm install && npm run buildClaude Code
claude mcp add threadflow -- node /path/to/dist/index.jsCursor (.cursor/mcp.json)
{ "mcpServers": { "threadflow": { "command": "node", "args": ["/path/to/dist/index.js"] } } }Streamable HTTP
node dist/index.js --http --port 3003 # serves MCP at http://127.0.0.1:3003/mcpDocker
docker build -t threadflow-mcp -f docker/Dockerfile .
docker run -d --name threadflow -p 3003:3003 threadflow-mcp
# MCP at http://127.0.0.1:3003/mcpThe draft/schedule registries are in-memory (lost on restart — re-draft before finalizing); this is workflow discipline, not a scheduler daemon.
Example session
> validate_thread(posts: [...])
→ per-post char counts, flags, issue list — none saved
> draft_thread(posts: [...])
→ draftId d-1a2b + validation report (blocking issues refuse the draft)
> post_thread(posts: [same exact text],
preflight: { score_offer(...) })
→ 82/100 (A) → cleared, audited
→ 38/100 (D) → GATE REFUSED, verbatim kill rule
> schedule_thread(posts: [...], run_at: "2026-10-28T16:00:00Z")
→ scheduleId s-3c4d, pending (dispatch happens in the ThreadFlow app)The chained workflow (the product story)
marketing-scope-mcp score_offer → threadflow-mcp draft_thread → post_thread
(whether) (what) (when/gate)An agent runs score_offer, drafts the thread, and threads the score through
preflight — the same enforced-discipline white space the marketing server
occupies, extended from planning to publishing.
License
MIT — see LICENSE.
Available Tools
4 toolsdraft_threadDraft a threadA
Validate a thread AND register the validated posts in the in-memory draft registry (keyed by the exact joined text; lost on restart — re-draft before finalizing). Returns the draftId and the validation report. post_thread/schedule_thread REJECT any posts array that was never drafted, with an error naming the exact text — the thread equivalent of the sibling's unscored-offer gate.
Inputs: posts (required).
post_threadPost a threadA
Mark a VALIDATED draft as cleared to post NOW. Requires the exact posts to have been drafted with draft_thread first (refuses unvalidated text) and honors the optional pre-flight kill-rule gate (score < 45 -> refusal, verbatim sibling rule). This tool records the audit line; the actual platform POST is executed by the ThreadFlow app's authenticated path — this server holds no X credentials by design.
Inputs: posts (required), preflight.
schedule_threadSchedule a threadA
Schedule a VALIDATED draft to run at an ISO-8601 UTC time. Requires the exact posts to have been drafted with draft_thread first (the registry refuses unvalidated text). Accepts the optional marketing pre-flight score — score < 45 returns the kill-rule refusal and schedules nothing. In-memory only (lost on restart); this is workflow discipline, not a scheduler daemon.
Inputs: posts (required), run_at (required), preflight.
validate_threadValidate a threadARead-onlyIdempotent
Run the per-post evidence check on a draft thread WITHOUT saving anything: 280-char platform limit per post, 25-post thread limit, empty-post detection, hook quality on post 1, and the links-on-final-post convention. Returns flags + an issue list WITH per-post evidence. Side effect: none (the registry only accepts drafts made with draft_thread).
Inputs: posts (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The four tools map to distinct workflow stages (validate, draft, schedule, post), and descriptions explicitly contrast validate_thread's no-side-effect dry run with draft_thread's registry write. The main residual overlap is that both validate and draft perform validation, so an agent could momentarily hesitate between them, but the side-effect distinction resolves it.
All four names follow a strict verb_noun snake_case pattern (validate_thread, draft_thread, schedule_thread, post_thread). The convention is predictable and the noun is consistent across the set.
Four tools is well-scoped for a narrow thread draft/validate/schedule/post workflow, and each tool clearly earns its place. Nothing feels padded or redundant.
The happy-path lifecycle is covered (validate -> draft -> schedule or post), but there is no way to edit a registered draft, list/inspect drafts, cancel a scheduled post, or discard a draft. The in-memory registry makes these gaps more painful, since a scheduled post cannot be unscheduled through the tool surface.
Maintenance
Related MCP Connectors
Your agent posts, schedules, queues and threads posts on X, with a human approval queue.
Threads scheduler for AI agents: write, schedule and publish posts, review replies, read insights.
Let AI agents post to social media with human approval: schedule, first comments, threads.
Guarded agent surface for X & LinkedIn: discover, score, and draft in your voice. No key can post.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables creating, managing, and publishing X/Twitter posts, threads, and replies directly through Claude chat. Supports draft management with the ability to create, list, publish, and delete tweet drafts.101MIT
- AlicenseAqualityDmaintenanceEnables AI agents to read, post, search, and engage with Twitter/X content, including AI-powered reply drafting and analytics.17MIT
- AlicenseAqualityBmaintenanceEnables AI agents to manage a Threads profile through Meta's API, including posting, threads, replies, reply moderation, and insights.3030 npm4MIT
- AlicenseAqualityBmaintenanceEnables AI agents to manage social media posts across multiple platforms by scoring virality, generating threads, converting formats, optimizing hooks, scheduling campaigns, and validating platform limits.12MIT