doom
Server Details
Obsolescence-risk screening: predicts if a product gets absorbed into core LLM-platform features.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Each tool has a clearly distinct purpose: prep, start assessment, poll result, list assessments, list signals, list candidates, overview, feedback, retire signal, review candidate, retire calibration case. No two tools appear to do the same thing, even the list tools differ by what they list (active vs candidate signals) and how they're used (poll vs list).
Tools mostly follow a verb_noun snake_case pattern (assess_product, get_assessment, list_assessments, record_outcome, retire_signal, etc.), but 'doom_prep' and 'overview' deviate from the verb_noun structure, making the naming slightly less consistent though still readable.
With 11 tools, the surface is well-scoped for a domain involving assessments, signal management, and calibration. Each tool earns its place, and the count fits comfortably within the ideal 3-15 range.
The toolset covers the full lifecycle: prep, assess, poll, list, overview, feedback, and signal/calibration management. Minor gaps exist (e.g., no way to view a single signal's details beyond listing, and no explicit update for assessments), but agents can work around them without significant failures.
Available Tools
11 toolsassess_productAInspect
Assess one product's obsolescence risk. Provide exactly ONE of description/url/pitch_company_id/deck_text. Async — returns job_id; poll get_assessment. Defaults to deep mode. Optionally pass requested_by to identify the caller (shown in the activity feed).
Inputs: url, mode, deck_text, description, +2 more.
doom_prepAInspect
Prep Gate. Validates config + confirms the roadmap-signals KB is within the staleness threshold. Fails closed if stale. Call before assess_product.
Inputs: no named parameters.
get_assessmentAInspect
Poll an assessment job_id. Returns status + the typed assessment when complete. Hard timeout — never hangs on pending.
Inputs: job_id (required).
list_assessmentsAInspect
Recent assessments, filterable by verdict.
Inputs: limit, verdict.
list_kb_signalsAInspect
List the active (signed, grounding) roadmap signals with their ids — use to find a signal_id to retire. Operator-only.
Inputs: operator_key (required).
list_signal_candidatesAInspect
KB-refresh review queue. List auto-scraped candidate roadmap signals (default: pending). Operator-only. Approve/reject with review_signal_candidate; the weekly cron signs approved ones into the live KB.
Inputs: operator_key (required), limit, status.
overviewBInspect
Inspectable State. No input. Counts, recent activity, roadmap-signal freshness, health, last calibration run.
Inputs: no named parameters.
record_outcomeAInspect
Outcome-feedback (learning loop). Record what ACTUALLY happened to a previously-assessed product as a labeled calibration case; the weekly recalibration folds it into the gate. Operator-only (requires operator_key). Provide either job_id (links the case to that assessment + reuses its product) or product text.
Inputs: operator_key (required), actual_outcome (required), expected_verdict (required), notes, +3 more.
retire_signalAInspect
UNLEARN a KB signal that became false/obsolete (e.g. a rumored feature cancelled, or a signal no longer predictive). Soft-deletes it (active=false) so it stops grounding assessments immediately — recoverable. Operator-only. Find the id via list_kb_signals.
Inputs: reason (required), signal_id (required), operator_key (required).
review_signal_candidateAInspect
Approve or reject a KB-refresh candidate signal. Operator-only. Approved candidates are signed (Ed25519) into the live roadmap_signals KB by the next refresh run; rejected ones are dropped. Controls what becomes grounding truth.
Inputs: action (required), candidate_id (required), operator_key (required).
supersede_calibration_caseAInspect
UNLEARN a calibration case whose label turned out wrong or obsolete — retires it (active=false) so the recalibration gate stops scoring it. To correct, retire the wrong case then record_outcome the right one. Operator-only.
Inputs: reason (required), case_id (required), operator_key (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
LLM SEO and Agent Discoverability for B2B SaaS. Pricing, fit assessment, audit requests.
LLM provider intelligence: recommendations, pricing, and status
Market & Company Intelligence for AI agents: next adoptions, company health, signals, market feeds.
Vendor intelligence for AI coding agents choosing developer tools and stacks.
Related MCP Servers
- AlicenseAqualityCmaintenanceA pre-action risk gate for AI agents. Your agent calls the forecast tool before any irreversible action — send email, run SQL, make a payment, delete a file — and gets a risk score (0–100) and a GO / CONFIRM / STOP verdict in a few seconds.173 npmMIT
- AlicenseAqualityAmaintenanceEnables agents to verify claims against cited evidence, screen content for prompt injection and relevance before reading it, and rank candidates by meaning, all with calibrated probability verdicts.124,169 npm580MIT
- AlicenseAqualityCmaintenanceEnables LLM application builders and security teams to detect and strip prompt injections, scan for secrets, obfuscate PII, and audit synthetic datasets for bias using deterministic tools.5MIT
- FlicenseNot gradedqualityBmaintenanceEnables autonomous agents to score customer leads and evaluate interaction velocity to predict conversions, exposing deterministic, zero-dependency evaluation as an MCP tool. Integrates with MCP clients like Claude Desktop and Cursor for programmatic lead assessment.8-
Glama MCP Gateway
Add one secure layer between your agents and this server.