Long form authoring pipeline — Atom
Server Details
Long-form authoring pipeline: outline, review and build record checked per call.
- Status
- Healthy
- Uptime
- 21.7% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- nrupala/atom-services
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection or overlapping purpose. The description clearly scopes it to a single audit action with a deterministic verdict.
The single name uses a clear snake_case convention matching the server's domain, but it is unusually long and encodes the whole workflow rather than a verb_noun action. With one tool there is no pattern to violate, only a mild deviation from crisp action naming.
A one-tool surface is borderline thin for a domain described as an entire authoring pipeline with six sections and multiple check families. It is defensible as an audit-only validator, but it leaves no granular entry points.
The tool covers the verdict lifecycle (sound / not sound / insufficient evidence) with per-check evidence, which is coherent for a read-only auditor. However, there is no companion operation to retrieve, submit, or amend the declared record, and no way to run individual section checks, making the surface a single dead-end call.
Available Tools
1 toollong_form_authoring_pipelineLong-form authoring pipelineARead-onlyIdempotentInspect
Submits a long-form authoring pipeline record (outline as contract, drafting loop, review passes, versioning and builds, publishing, feedback loop and red lines) and returns a deterministic AUTHORING_PIPELINE_SOUND / AUTHORING_PIPELINE_NOT_SOUND / INSUFFICIENT_EVIDENCE verdict across six sections, including computed per-unit single-point and review-pass coverage checks, with per-check evidence. Audits the declared record; it writes nothing and runs no build.
Inputs: work, units, builds, review, +7 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Publish agent output to permanent versioned URLs, read review comments back, and revise.
Finance education article production-record audit, delivered per API call as an atom on Conduit.
Human-owned review for agent plans, rendered documents, Forms, research, and live previews.
Draft SEO blog articles from topic to ready-to-review post.
Related MCP Servers
- FlicenseAqualityCmaintenanceEnables users to create and refine a research outline, queue report generation in the background, and retrieve progress or completed Markdown reports, with automatic checkpointing so unfinished work can resume after a restart.4-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to draft long-form web novels with persistent, disk-backed memory, assembling a pre-writing task brief from structured settings, outlines, foreshadowing ledgers, and timelines, then committing post-chapter fact increments. It also audits pacing, checks per-chapter six-dimension consistency, gates commits on unresolved review findings, and can replay the commit chain to rebuild state when records and manuscripts disagree.1MIT
- AlicenseNot gradedqualityBmaintenanceAuthor verifiable eval records through a draft → review → revise → submit loop with server-enforced graders; compile to JSONL/CSV/Inspect/lm-eval via MCP.347 npm1Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI hosts to plan, draft, and check long-form novel chapters while honoring canon settings, character state, arcs, and check ordering, with approval-gated atomic commits. It keeps world, character, and chapter files as the human-editable source of truth, with snapshots and rollback for recovery.2717 npmApache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.