Assessment · Governance · Assess and know

8MCP servers, tools and AI supply chain

Which tools and components can our agents reach, and can we trust them?

Every MCP server, plugin, model source and library an AI system depends on.

AutomatedStakeholder interviews 2 controls 3 engines

How we collect

  • AutomatedMCP configs and the tools each agent can callNeeds your export or setup
  • AutomatedAgent 365 catalog when licensed (absence is reported)Needs your export or setup
  • AutomatedOpen-weight and self-hosted models and their originRuns today
  • Stakeholder interviewsEngineering: build and deployment pipelineRuns today

Status labels show what runs today, what needs an export or setup from you, and what is planned.

What you get

  • Dependency map per workflow
  • Approved tool descriptions hashed so later changes show
  • Untrusted or unreviewed MCP servers and tools

Questions we ask

  • Which external tools can your agents call?

We can start from

SBOMs, software composition reports

Data sources

SourceWhat we readStatus
QuestionnaireThe short interview for what data cannot show: purpose, owners, decisions AI informs, regulations in scope.Runs today
Microsoft Graph and Entra IDService principals, OAuth grants, app registrations, sign-ins to AI apps, Copilot usage reports. Read-only scopes, metadata only.Runs today
AI gateway telemetryLiteLLM, Cloudflare AI Gateway or AICost CostWall logs: cost per team, workload, agent and outcome.Partly automated

Built on governance engine modules

P4 PlannedAgents, MCP & Autonomous Actions

What can your agents actually do, and who approved it?

Security & Assurance
P2 BetaAI Security & Data Leakage

Where can data leak through AI, and what stops it?

Security & Assurance

AICost governance controls in this module

AICost-GovControl403Partly automated
MCP servers and agent connectors
What it is

Intake and review of MCP servers and other connectors that give agents tools and data, with scoped credentials.

Why it is needed

Each connector is a new path to data and actions. Untrusted tool output can carry instructions an agent will follow.

Why enterprises need it

Teams adding MCP servers need a review step, credentials scoped per connector, and a list of what each one exposes.

What you get:Connectors reviewed before useScoped, revocable credentialsTool output treated as data, not instructions
Run by
Agents, MCP and Autonomous Actions engineTool Integrations engine
Data
Questionnaire, Microsoft Graph and Entra ID
Evidence produced
Connector register: server, owner, tools exposed, data reachable, credential scope, review date.
Maps to
OWASP Top 10 for LLM: prompt injection; NIST AI RMF: Manage
AICost-GovControl703Partly automated
AI supply chain
What it is

The upstream parts each AI system depends on: foundation models, datasets, tools, hosting and compute, and the risk of each.

Why it is needed

A failure or change upstream can stop your service or change its behavior.

Why enterprises need it

Resilience planning needs a list of dependencies and a fallback for the critical ones.

What you get:Critical dependencies listedFallbacks plannedConcentration risk reduced
Run by
AI Architecture Decision engineVendor Lock-in Risk engineModel Origin Risk engine
Data
Questionnaire, AI gateway telemetry
Evidence produced
Dependency map: system, dependency, type, provider, criticality, fallback.
Maps to
NIST AI RMF: Map; ISO/IEC 42001: supplier relationships

Frameworks

OWASP Top 10 for LLMPrompt injection, data leakage, excessive agency, supply chain

Stakeholders

CISOEngineeringAI platform owner
← 7. Identity, access and agent permissions All modules 9. Vendor and model due diligence →
📖 Data sources & methodology 172 text models · 9 embeddings · 44 vision · 62 audio · 8 vector DBs across 10 vendor pages · last verified 2026-10-18

Methodology

  • All prices are USD per 1 million tokens, current as of 2026-10-18.
  • Vendor-published values have no mark. Inferred/extrapolated values are marked with * and listed below.
  • Batch API discounts are 50% off standard rates across providers that offer Batch mode.
  • Prompt caching discounts vary by provider (typically 80-90% off cached input tokens).
  • Regional data-residency surcharges (Anthropic 1.1x, OpenAI 1.1x, Google regional tiers) are NOT included in base rates.
  • Long-context pricing tiers apply when input exceeds model threshold.
  • Embedding prices are input-only (no output tokens generated).

Primary sources

Last-verified date is the most recent successful daily snapshot (aicost_pricing_snapshots) or, when no snapshot exists yet, the latest successful crawler run (aicost_crawler_runs). 10 of 10 vendors are currently verified. Aggregator services (TokenCost, AI Pricing Guru, etc.) are not listed.

Anthropic
2026-10-18
https://www.anthropic.com/pricing
Daily snapshot since Sep 2023 · 704 days captured
Anthropic Docs
2026-10-18
https://platform.claude.com/docs/en/about-claude/pricing
Daily snapshot since Sep 2023 · 704 days captured
OpenAI
2026-10-18
https://openai.com/api/pricing/
Daily snapshot since Sep 2023 · 705 days captured
Google AI
2026-10-18
https://ai.google.dev/gemini-api/docs/pricing
Daily snapshot since Dec 2023 · 680 days captured
Google Vertex
2026-10-18
https://cloud.google.com/vertex-ai/generative-ai/pricing
Daily snapshot since Dec 2023 · 680 days captured
DeepSeek
2026-10-18
https://api-docs.deepseek.com/quick_start/pricing
Daily snapshot since May 2024 · 619 days captured
xAI
2026-10-18
https://x.ai/api
Daily snapshot since Nov 2024 · 537 days captured
Mistral
2026-10-18
https://mistral.ai/pricing
Daily snapshot since Dec 2023 · 678 days captured
Cohere
2026-10-18
https://cohere.com/pricing
Daily snapshot since Sep 2023 · 704 days captured
Voyage AI
2026-10-18
https://docs.voyageai.com/docs/pricing

Inferred values (marked with * in calculator tables)

Derived from industry conventions, not directly published by the vendor. Typical conventions: cached input = 10% of base (90% off), Batch API = 50% of base (50% off).

Vendor / Model Field Why it’s inferred
Anthropic — Claude Sonnet 4.6 cachedInput Derived at 10% of input rate — Anthropic publishes 90% cache-hit discount on this tier.
Anthropic — Claude Sonnet 4.5 cachedInput Derived at 10% of input rate; same 90% cache-hit convention as Sonnet 4.6.
Anthropic — Claude Sonnet 4.5 batchInput Derived at 50% of standard input — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Sonnet 4.5 batchOutput Derived at 50% of standard output — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Haiku 4.5 cachedInput Derived at 10% of input rate — Anthropic 90% cache-hit discount convention.
OpenAI — GPT-5.4 Mini cachedInput Derived at 10% of input — OpenAI documents automatic 90% discount on cache hits across GPT-5.x tier.
OpenAI — GPT-5.4 Nano cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Nano batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Nano batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Pro batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.2 cachedInput Derived at 10% of input; no residency uplift.
OpenAI — GPT-5.2 batchInput Derived at 50% of input.
OpenAI — GPT-5.2 batchOutput Derived at 50% of output.
OpenAI — GPT-5 cachedInput Derived at 10% of input.
OpenAI — GPT-5 batchInput Derived at 50% of input.
OpenAI — GPT-5 batchOutput Derived at 50% of output.
OpenAI — GPT-5.5 Pro cachedInput Derived at 10% of input — OpenAI does not publish a cached rate for *-pro models; using the family convention.
OpenAI — GPT-5.5 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5.5 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5.2 Pro cachedInput Derived at 10% of input — pro-tier convention.
OpenAI — GPT-5.2 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5.2 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5.1 batchInput Derived at 50% of input.
OpenAI — GPT-5.1 batchOutput Derived at 50% of output.
OpenAI — GPT-5 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5 Nano cachedInput Derived at 10% of input.
OpenAI — GPT-5 Nano batchInput Derived at 50% of input.
OpenAI — GPT-5 Nano batchOutput Derived at 50% of output.
Google — Gemini 3 Flash cachedInput Derived at 10% of input — Google caching discount convention ~90%.
Google — Gemini 3.1 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
Google — Gemini 3.1 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 3.1 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Pro cachedInput Derived at 10% of input.
Google — Gemini 2.5 Flash cachedInput Derived at 10% of input.
Google — Gemini 2.5 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
Google — Gemini 2.5 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
xAI — Grok 4 (legacy) cachedInput Extrapolated at 25% of base.

Pricing is cross-verified against the LiteLLM community registry when available. Daily snapshots are kept in aicost_pricing_snapshots; every change is logged to aicost_price_changelog with old & new values for full audit trail. Read the full methodology →