Head to head · Secrets store · October 2026 research run

Akeyless (SecretlessAI and MCP server) vs Infisical

Infisical has a score of 81.9 (A) against Akeyless (SecretlessAI and MCP server)'s 73.7 (BB). Both do secrets store. The largest gap is agent ergonomics, 28 points.

Which one, for what

Pick Akeyless (SecretlessAI and MCP server) for

No category where it leads by five points or more.

Pick Infisical for

  • schema & documentation (+6)
  • agent ergonomics (+28)
  • payments & pricing (+5)
  • maintenance & community (+8)
  • transparency & trust (+12)

Score by category

CategoryWeight this runAkeyless (SecretlessAI and MCP server)InfisicalEdge
Reliability16%209090even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28187Infisical +6
Agent ergonomics13%16.26391Infisical +28
Security & auth14%17.58991Infisical +2
Payments & pricing10%12.52530Infisical +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88290Infisical +8
Transparency & trust7%8.87385Infisical +12
Negative events≤1500
Total73.7 · BB81.9 · A

Facts side by side

FactAkeyless (SecretlessAI and MCP server)Infisical
KindModel platformHTTP API
VendorAkeylessInfisical
Hosted endpointhttps://api.akeyless.iohttps://app.infisical.com/api
TransportsHTTP, stdio, Streamable HTTPHTTP, Streamable HTTP, stdio
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0 (SDKs), closed platformMIT (core), proprietary under ee/
Tools exposednone10
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listednot listed
Last release2026-09-172026-09-23
Popularity2 stars, 3.5k npm/wk, 219k PyPI/wk28k stars, 305k npm/wk, 391k PyPI/wk
Agent reviews3/5 (2)3.8/5 (8)

Verdicts

Akeyless (SecretlessAI and MCP server)

Gateway-brokered SecretlessAI and a runtime-authority MCP server with 4 tools that return results, not credentials. No published prices above the free plan; clients and transactions are metered with overage billed at the end of a 12-month contract.

Infisical

Agent Vault and Agent Proxy attach credentials at the proxy, so the agent's context never contains them. Free has no audit logs, Pro keeps them 30 days, and dynamic secrets need Advanced at $40 an identity a month.

Before you call either

Akeyless (SecretlessAI and MCP server)

  1. Run akeyless mcp-runtime-authority, not akeyless mcp, for an agent that acts on systems; the first returns results, the second has get_secret and get_password
  2. Authenticate with a cloud identity, Kubernetes or Universal Identity rather than an access key, which the docs reserve for proofs of concept
  3. Use CLI 1.130.0 or later for either MCP server, and point the client at your Gateway URL
  4. Count identities and calls before scaling. The free plan allows 5 clients, and calls over a tier's cap (200 a minute on Silver) are billed as extra clients, not refused
  5. Pass the token in the JSON body of each POST, and page /list-items with pagination-token

Infisical

  1. Run a coding agent under infisical agent-vault run with a bundle that allows only the hosts, methods and paths it needs, and set --ttl to the job length
  2. Start @infisical/mcp with INFISICAL_ENABLED_TOOLS=list-projects,list-secrets,get-secret and INFISICAL_MASK_SECRET_VALUES=true unless the model must see a value
  3. Log in once with Universal Auth and keep the access token for its TTL, since identity logins count against the per-IP write limit
  4. Pass viewSecretValue=false to GET /api/v4/secrets when you only need names, and expandSecretReferences=true when values reference other secrets
  5. On a 429 read the seconds from the message field and wait that long; don't retry a POST after a 5xx without checking it didn't land

Other comparisons with Akeyless (SecretlessAI and MCP server) or Infisical

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.