On this page
How to choose an AI gateway
for agents that touch real systems.
Verosek is an AI and MCP gateway: keep your SDK, route model calls with fallback, set budgets and rate limits per key, connect your tools, and have each tool call decided by the key's rules before it runs. Moving takes two values, base URL and key.
Which kind of tool do you need?
Verosek is for a platform or infrastructure team whose own agents write to production databases and APIs, and who has to show what an agent did. New to the words? Here is what a router, an AI gateway, an AI firewall and an MCP gateway each do.
You want one gateway for model calls and your agents' tool calls, with rules that read what each call does.
Verosek routes model calls, sets budgets and rate limits per key, connects your tools, decides each tool call before it runs, and seals a record of each request.
You want the widest provider list.
LiteLLM is an open-source gateway you host, with over 140 providers.
You pick a gateway by speed at high volume.
Bifrost is a high-performance open-source gateway across 23+ providers.
You want prompt tooling and a hosted control plane.
Portkey offers prompt templates, a playground and versioning, with a control plane it hosts.
You train and serve your own models.
TrueFoundry is an AI gateway for models, MCP and agents, on a platform that also trains and deploys models.
You run MCP servers in containers on a workstation.
Docker MCP Gateway runs each server in a restricted container, and its open-source gateway is built into its MCP Toolkit.
Questions to ask any AI gateway
Ask each vendor these, on your own queries and your own tools. Here is how Verosek answers.
| The question | Verosek's answer |
|---|---|
| Which providers does it route to, and what happens when one fails? | Verosek routes to OpenAI, Anthropic, Google, Azure, Bedrock, Ollama and any OpenAI-compatible server. Calls fall back in priority order, with retries and cooldown after failures, and a residency rule is checked before any call. |
| Can each key carry its own budget and limits? | Yes. Each key carries its allowed models, budget, rate limits, expiry and per-tool rules. |
| What does a tool rule read? | The call itself. For a database tool Verosek runs, it reads the SQL statement itself, so a key can read one table and be refused a DELETE on any of them. |
| What happens to a tool with no rule? | A tool Verosek runs is refused, and not offered to the model, until the key has a rule for it. |
| What happens when a check cannot run? | Each key sets each check to enforce, flag or log, so you choose what stops a call and what only leaves a note. By default a blocking rule that cannot run refuses, and you can set one rule on a key to let calls through when the check itself breaks. |
| What happens when a tool call times out? | Verosek tells the agent the tool timed out and treats the call as one that may have run: if a check you set to enforce then cannot run, the answer says which calls ran and tells the agent not to repeat them yet. |
| Who can check the record later? | Give a regulator your public keys, and they can check each decision themselves. You can verify a trace through the API. |
| Where can it run, and on which plan? | Enterprise: private cloud, VPC or air-gapped, deployed with us |
| What does it cost, and is the price published? | Team is $999 a month, billed yearly. Enterprise has custom terms. Both plans start with a call. |
Six tools at a glance
| The point | Verosek | LiteLLM | Portkey | Bifrost | TrueFoundry | Docker MCP Gateway |
|---|---|---|---|---|---|---|
| Built for | One gateway for model calls and tool calls, with rules that read each call | Routing to over 140 providers, with spend controls | One interface to over 3,000 models | High-performance routing across 23+ providers | An AI gateway for models, MCP and agents, on a platform that also trains and deploys models | Running MCP servers in containers |
| Model routing | OpenAI, Anthropic, Google, Azure, Bedrock, Ollama and any OpenAI-compatible server, with fallback | Over 140 providers, with fallbacks in open source | Over 3,000 models, with fallback | 23+ providers, with failover | Over 1000 LLMs, with failover | Open source: Running and proxying MCP servers in containers. |
| Tool rules | Per key and per tool, before each call runs: a SQL statement's operation, tables and row bounds, a payment's amount, a file path, a namespace, a recipient | Allow lists at six levels, per key and team among them, with patterns on values | Tool switches and text and structure checks | Allow lists per key; guardrails on arguments on Enterprise | Cedar or OPA policies you write | Open source: Allow lists by profile.AI Governance: Cedar rules on values. |
| Scanning | Prompt injection, personal data and secrets in prompts, replies, tool arguments and tool results, on both plans, with no second vendor to buy | A guardrail framework in open source; guardrails per key or team on Enterprise | Deterministic checks on Developer, LLM and partner checks on Production | Guardrails on Enterprise | Built-in guardrails from Pro | Open source: A scan for secret-like values. |
| The record | One sealed record for each request, with the reason for each decision | Request logs through callbacks; admin audit logs on Enterprise | Logs of each MCP request; Audit Logs of admin actions on Enterprise | Request logs; signed audit logs of admin activity on Enterprise | Metadata audit logs of platform activity from Pro | Open source: Tool names and argument shape.AI Governance: Metadata records, without parameter values. |
| Where it runs | Enterprise: private cloud, VPC or air-gapped, deployed with us | Open source: self-hosted; hosted through sales | Enterprise: managed SaaS or hybrid; open source: a self-hosted MIT gateway | Open source: self-hosted; Enterprise: VPC, on-prem and air-gapped | Hosted; Enterprise: VPC and on-prem | Open source: Any Docker Engine.Enterprise Gateway: Your own account, or air-gapped. |
As of 5 Nov 2026.
Attacks become findings, and findings become rules on the key.
Assay, an open MCP security benchmark we maintain, was presented at Black Hat India Arsenal. Our red-team framework holds 205 attack techniques, 68 for MCP, with findings anyone can recompute.
Frequently Asked Questions
If you want one gateway for model calls and your agents' tool calls, with rules that read what each call does, talk to Verosek. Each key carries its allowed models, budget, rate limits, expiry and per-tool rules. For a database tool Verosek runs, it reads the SQL statement itself, so a key can read one table and be refused a DELETE on any of them. Model calls and tool calls land in one sealed record, with the reason for each decision.
With Verosek, no: the checks ship in the gateway, so there is no second vendor to buy, no second key and no second record. Turn on Shield and each key's checks look for prompt injection in prompts, tool arguments and tool results, and for personal data and secrets in those and in replies. If your gateway reaches a scanner through an integration, ask what that adds: an account, a key, a console, a bill, and where your text goes.
If your agents also call tools against production systems, add Verosek to the list: one gateway for both, with rules that read each call. LiteLLM has an open-source core you host, and Portkey's commercial product comes as managed SaaS or hybrid. As of 5 Nov 2026.
Verosek routes too, with rules that read each tool call on the same key. Bifrost sells on performance, and LiteLLM on reach, with over 140 providers. As of 5 Nov 2026.
Verosek puts model calls and tool calls on one key. Docker's open-source gateway runs MCP servers in containers, and TrueFoundry is an AI gateway for models, MCP and agents, on a platform that also trains and deploys models. As of 5 Nov 2026.
Verosek can. On the Enterprise plan it can run wholly in your environment, deployed with us: private cloud, VPC or air-gapped. Among the others, LiteLLM offers it on Enterprise, Bifrost on Enterprise, TrueFoundry on Enterprise and Docker on its Enterprise Gateway. Portkey has closed it to new customers. As of 5 Nov 2026.
Verosek is the gateway as well: one key routes your model calls, Bedrock among them, sets budgets and scans with no second vendor, and it reads the SQL statement and seals the reason for each decision. AgentCore Policy goes by user identity, a tool call's input parameters, earlier steps in the session and signals such as a guardrail's score; its docs do not say a policy reads a SQL statement. As of 5 Nov 2026.
Verosek is closed source. The gateway and its admin console hold no licence check, telemetry, analytics or call to a Verosek host.
Team is $999 a month, billed yearly. Enterprise has custom terms. Both plans start with a call. See the plans.
By default a blocking rule that cannot run refuses, and you can set one rule on a key to let calls through when the check itself breaks. A check that only flags lets the text through and names it in a response header. A request the record cannot hold is refused before anything runs.
An app leaves by changing the same two values. On a self-hosted deployment, on the Enterprise plan, the gateway, its signing key and your records stay with you.
Bring one real agent to a call, and we stand up a gateway for it.
Sources
- AWS docs: policy https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy.html Read 6 Nov 2026
- Bifrost docs: audit logs https://docs.getbifrost.ai/enterprise/audit-logs Read 5 Nov 2026
- Bifrost docs: default https://docs.getbifrost.ai/features/observability/default Read 5 Nov 2026
- Bifrost docs: guardrails https://docs.getbifrost.ai/enterprise/guardrails Read 5 Nov 2026
- Bifrost docs: mcp tools https://docs.getbifrost.ai/features/governance/mcp-tools Read 5 Nov 2026
- Bifrost on GitHub https://github.com/maximhq/bifrost Read 5 Nov 2026
- Docker docs: audit https://docs.docker.com/ai/governance/organization/audit/ Read 5 Nov 2026
- Docker docs: mcp gateway https://docs.docker.com/ai/mcp-catalog-and-toolkit/mcp-gateway/ Read 5 Nov 2026
- Docker docs: mcp policy https://docs.docker.com/ai/governance/reference/mcp-policy/ Read 5 Nov 2026
- Docker on GitHub https://github.com/docker/mcp-gateway Read 5 Nov 2026
- Docker on GitHub: mcp gateway.md https://github.com/docker/mcp-gateway/blob/main/docs/mcp-gateway.md Read 5 Nov 2026
- Docker on GitHub: security.md https://github.com/docker/mcp-gateway/blob/main/docs/security.md Read 5 Nov 2026
- Docker: mcp enterprise gateway https://www.docker.com/products/mcp-enterprise-gateway/ Read 5 Nov 2026
- LiteLLM https://www.litellm.ai/ Read 5 Nov 2026
- LiteLLM docs: audit logs https://docs.litellm.ai/docs/proxy/audit_logs Read 5 Nov 2026
- LiteLLM docs: enterprise https://docs.litellm.ai/docs/enterprise Read 5 Nov 2026
- LiteLLM docs: llms.txt https://docs.litellm.ai/llms.txt Read 5 Nov 2026
- LiteLLM docs: mcp control https://docs.litellm.ai/docs/mcp_control Read 5 Nov 2026
- LiteLLM docs: security owasp llm top10 https://docs.litellm.ai/docs/proxy/security_owasp_llm_top10 Read 5 Nov 2026
- LiteLLM docs: tool permission https://docs.litellm.ai/docs/proxy/guardrails/tool_permission Read 5 Nov 2026
- LiteLLM: pricing https://www.litellm.ai/pricing Read 5 Nov 2026
- Maxim AI: pricing https://www.getmaxim.ai/pricing Read 5 Nov 2026
- Portkey on GitHub https://github.com/Portkey-AI/gateway Read 5 Nov 2026
- Portkey: architecture https://portkey.ai/docs/self-hosting/hybrid-deployments/architecture Read 5 Nov 2026
- Portkey: audit logs https://portkey.ai/docs/product/enterprise-offering/audit-logs Read 5 Nov 2026
- Portkey: fallbacks https://portkey.ai/docs/product/ai-gateway/fallbacks Read 5 Nov 2026
- Portkey: guardrails https://portkey.ai/docs/product/mcp-gateway/guardrails Read 5 Nov 2026
- Portkey: observability https://portkey.ai/docs/product/mcp-gateway/observability Read 5 Nov 2026
- Portkey: pricing https://portkey.ai/pricing Read 5 Nov 2026
- Portkey: product feature comparison https://portkey.ai/docs/product/product-feature-comparison Read 5 Nov 2026
- Portkey: tool provisioning https://portkey.ai/docs/product/mcp-gateway/tool-provisioning Read 5 Nov 2026
- Portkey: welcome https://portkey.ai/docs/aigw/introduction/welcome Read 5 Nov 2026
- TrueFoundry: audit logging https://www.truefoundry.com/docs/platform/audit-logging Read 5 Nov 2026
- TrueFoundry: cedar guardrails https://www.truefoundry.com/docs/ai-gateway/cedar-guardrails Read 5 Nov 2026
- TrueFoundry: llms.txt https://www.truefoundry.com/llms.txt Read 5 Nov 2026
- TrueFoundry: modes of deployment https://www.truefoundry.com/docs/ai-gateway/modes-of-deployment Read 5 Nov 2026
- TrueFoundry: opa guardrails https://www.truefoundry.com/docs/ai-gateway/opa-guardrails Read 5 Nov 2026
- TrueFoundry: pricing https://www.truefoundry.com/pricing Read 5 Nov 2026
- TrueFoundry: virtual model https://www.truefoundry.com/docs/ai-gateway/virtual-model Read 5 Nov 2026

