DeepSecureBLOCK
Effortlessly secure your AI agents and AI-powered workflows — from prototype to production. Get easy-to-use identity, credential, and access management built for fast-moving AI developers.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
DeepSecure: Effortless Identity & Auth for AI Agents
7d74f4d01c76OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add deepsecure --env ACCESS_TOKEN_EXPIRE_MINUTES=${ACCESS_TOKEN_EXPIRE_MINUTES} --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env API_KEY=${API_KEY} --env BACKEND_API_TOKEN=${BACKEND_API_TOKEN} -- uvx deepsecure{
"mcpServers": {
"deepsecure": {
"command": "uvx",
"args": [
"deepsecure"
],
"env": {
"ACCESS_TOKEN_EXPIRE_MINUTES": "${ACCESS_TOKEN_EXPIRE_MINUTES}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"API_KEY": "${API_KEY}",
"BACKEND_API_TOKEN": "${BACKEND_API_TOKEN}"
}
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
OpenAIAnalysis | read | Analyze data and extract insights using OpenAI API |
TavilySearch | read | Search the web for current information using Tavily API |
UniversalAI | read | Perform AI analysis using shared AI API credentials |
UniversalStorage | read | Store data using shared storage credentials |
UniversalWebSearch | read | Search the web using shared search API credentials |
Trust audit
BLOCKgrade F · trust 42/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (8 observation(s))
- Network
- declared (13 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
.env
if os.path.exists("/root/.kube/config") or os.path.exists(os.path.expanduser("~/.kube/config")):aws_creds_path = os.path.expanduser("~/.aws/credentials")azure_config_path = os.path.expanduser("~/.azure/config")"http://169.254.169.254/latest/meta-data/instance-id",
"http://169.254.169.254/metadata/instance?api-version=2021-02-01",
IMDS_URL = "http://169.254.169.254/metadata/identity/oauth2/token"
"http://169.254.169.254/metadata/instance?api-version=2021-02-01",
- DATABASE_URL=postgresql://deepsecure_user:deepsecure_password@db/deeptrail_controldb
print(f"DeepSecure Deeptrail Control API Token (effective): {token}")# logger.info(f"[AUTH_DEBUG] Token received by deeptrail-control: '{token}'")# logger.warning(f"[AUTH_DEBUG] Token mismatch: Received '{token}' vs Expected '{settings.BACKEND_API_TOKEN}'")# logger.info(f"[AUTH_DEBUG] Token validation successful for: '{token}'")export DEEPSECURE_DEEPTRAIL_CONTROL_URL="http://127.0.0.1:8000"
"http://169.254.169.254/latest/meta-data/instance-id",
"http://169.254.169.254/metadata/instance?api-version=2021-02-01",
IMDS_URL = "http://169.254.169.254/metadata/identity/oauth2/token"
- DATABASE_URL=postgresql://deepsecure:deepsecure@db_test:5432/deepsecure_test
- Control Plane connects to database at `postgresql://deepsecure_user:deepsecure_password@db/deeptrail_controldb`
- DATABASE_URL=postgresql://deepsecure_user:deepsecure_password@control-db/deeptrail_controldb
secret = "cannot-recover-with-one-share"
secret = "test-secret-for-validation"
assert private_pem.startswith("-----BEGIN PRIVATE KEY-----").envrc
.env
Gates applied: no_behavioural_pass.
7d74f4d01c76full audit observations/trust-audit/mcp-server/deeptrail__deepsecure.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 7d74f4d01c76 | BLOCK | F | 42 | first audit |
Questions
What is the DeepSecure MCP server?
Effortlessly secure your AI agents and AI-powered workflows — from prototype to production. Get easy-to-use identity, credential, and access management built for fast-moving AI developers.
What tools does DeepSecure expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is DeepSecure safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (42/100) and found 9 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does DeepSecure need?
It reads ACCESS_TOKEN_EXPIRE_MINUTES, ANTHROPIC_API_KEY, API_KEY, BACKEND_API_TOKEN, COMPOSIO_API_KEY, DEEPSECURE_API_TOKEN, DEEPSECURE_BACKEND_API_TOKEN, DEEPSECURE_DEEPTRAIL_CONTROL_API_TOKEN, DEEPSECURE_JWT_SECRET_KEY, DOCKER_RUNTIME_SECRET, GATEWAY_INTERNAL_API_TOKEN and SECRET_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does DeepSecure run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as deepsecure.
How current is this page?
The grade is for one exact copy of the source (7d74f4d01c76), read on 2026-10-08. The repository is watched and re-audited when it changes.