Tech stack decision memo — Atom
Server Details
Tech stack decision memo: declared stack decision memo record checked per call.
- Status
- Healthy
- Uptime
- 39.1% 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 selecting the wrong one. Its scope (audit a declared tech-stack memo and return a verdict) is stated explicitly, including what it does not do (no recommendation, no ranking).
With a single tool, there is no competing convention to clash with, and the snake_case name `tech_stack_decision_memo` is descriptive and readable. It is a noun phrase rather than a verb_noun action, but that is a minor stylistic point, not an inconsistency.
One tool is defensible because the server performs a single atomic submit-and-verdict operation, but the surface feels thin for a seven-section audit with reference, weighted-score, and consistency checks. Those sub-checks could plausibly have been exposed as separate inspection tools.
The write/validate path is fully covered, but there is no way to retrieve a previously submitted memo, list memos, or re-run a verdict on a stored record, and no tool to inspect the per-check evidence separately. Agents can work around this only by resubmitting the full memo each time.
Available Tools
1 tooltech_stack_decision_memoTech stack decision memoARead-onlyIdempotentInspect
Submits a tech-stack decision memo record (context and constraints, declared candidate rows and boring-technology declarations, evaluation criteria rows and evidence, total-cost and operability declarations, decision and rationale, reversibility and exit declarations, red lines) and returns a deterministic TECH_STACK_DECISION_SOUND / TECH_STACK_DECISION_NOT_SOUND / INSUFFICIENT_EVIDENCE verdict across seven sections, including computed criterion-reference, weighted-score recomputation and decision-candidate consistency checks over the declared rows, with per-check evidence. Audits the declared memo record only; it recommends no stack, picks no stack and ranks no candidate.
Inputs: tco, context, criteria, decision, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Structured decision making: declared decision record and its weighted matrix checked per call.
Semantic html review: declared semantic-HTML review record checked per call.
Poc design kill criteria verdict: declared POC design record checked per call.
ML project framing review: declared framing record checked per call.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables read-only MCP clients to query decision records, trace their cited sources, assess which decisions a planned code change touches, and identify decisions needing review before edits.42 PyPI2Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI clients to append durable, content-hashed records of each decision to an owner-controlled markdown notes folder, then recall them across sessions and across different tools with their dates, project provenance, and the exact note versions cited. Records are append-only and searchable by full text, topic stance, or recent activity, so past conclusions can be revisited without relying on an ephemeral session.3317 npmMIT
- AlicenseNot gradedqualityFmaintenanceArchitectural decision tracker with staleness detection — records decisions and alerts when code changes invalidate them.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to record and retrieve architectural decision records, check precedent before making decisions, and avoid repeating past mistakes or contradicting settled choices.39 PyPI4Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.