Trust Engine AI: model retirements and agent cost
dinevdecor/trust-engine-mcp
Model retirement dates with sources, public cost-vs-quality benchmark, local usage-cost check. Free.
- tools
- 8
- transport
- STDIO
- env var
- 1
- last updated
- Nov 12, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
check_my_modelsFor each model your agent uses: retirement date per platform, days left, the vendor's replacement, the source, and the next step ("re-test before ...")
For each model your agent uses: retirement date per platform, days left, the vendor's replacement, the source, and the next step ("re-test before ...")
No parameter schema in public metadata yet.
model_retirementsUpcoming retirements and deprecations, filtered, with sources
Upcoming retirements and deprecations, filtered, with sources
No parameter schema in public metadata yet.
analyze_usageSpend by model, top-model share, models on the retirement calendar, cost drivers, next steps. Runs offline; nothing is uploaded
Spend by model, top-model share, models on the retirement calendar, cost drivers, next steps. Runs offline; nothing is uploaded
No parameter schema in public metadata yet.
benchmark_resultsPublic Aider benchmark for Claude Opus, Sonnet and Haiku 5.5: tasks solved, cost per solved task, failed tasks, method and raw data
Public Aider benchmark for Claude Opus, Sonnet and Haiku 5.5: tasks solved, cost per solved task, failed tasks, method and raw data
No parameter schema in public metadata yet.
estimate_switch_savingsMeasured cost ratio and the arithmetic, for measured pairs only
Measured cost ratio and the arithmetic, for measured pairs only
No parameter schema in public metadata yet.
prepare_pilot_tasksThe pilot task format (CSV template), how to pick 20-30 tasks, how to mask personal data, and an offline check of a draft
The pilot task format (CSV template), how to pick 20-30 tasks, how to mask personal data, and an offline check of a draft
No parameter schema in public metadata yet.
request_pilotA draft e-mail and mailto: link to hello@agenttrustapi.com for a person to send
A draft e-mail and mailto: link to hello@agenttrustapi.com for a person to send
No parameter schema in public metadata yet.
pricingPublished prices (US$, valid from 12 Nov 2026), incl. the fixed-price 7-day test ($1,390), 24/7 watch and Bulgarian review
Published prices (US$, valid from 12 Nov 2026), incl. the fixed-price 7-day test ($1,390), 24/7 watch and Bulgarian review
No parameter schema in public metadata yet.
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageConfiguration
TRUST_ENGINE_OFFLINEdefault: 0Set to 1 to never fetch and use only the bundled data snapshot.
Readme
trust-engine-mcp
Free MCP server from Trust Engine AI. It answers questions agents otherwise search the web for:
- Which AI models does this code use, and are any being retired?
scan_for_modelsfinds the model ids in the working directory (read-only, on your machine) and checks them against the calendar. The same scan runs as a command (trust-engine-mcp check) and as a GitHub Action, without an agent. - Is a model we use being retired, and when? Verified dates for Anthropic, OpenAI, Google Gemini API and Vertex AI, AWS Bedrock and Mistral. Each date has its official source URL and the date it was checked.
- Why do our agents cost so much? It reads an OpenAI or Anthropic usage/cost export locally and shows spend by model, cost drivers and the fixes you can make yourself.
- Is a cheaper model good enough? You get our public benchmark numbers, a savings estimate for the model pairs we measured, and a ready request for a free pilot on your own tasks.
Details
- Repository
- github.com/dinevdecor/trust-engine-mcp
- Website
- agenttrustapi.com
- Package
trust-engine-mcp- Transport
- STDIO
- Registry
- MCP registry, active