ai-platform-engineering (caipe-io/ai-platform-engineering) is an MCP server listed on the M8ven Trust Index. It scores 45 out of 100, grade D. It declares 639 tools. No publisher has claimed this listing.

D
Warning
45/100

ai-platform-engineering

CAIPE is an open-source AI platform for building, governing, and operating AI agents and agentic workflows for platform engineering and beyond.

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

caipe-io

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Reads files from sensitive locations
Touches: ~/.aws
🔐
You'll be asked for 4 credentials: SCHEDULER_SERVICE_TOKEN, CAIPE_AGENT_CONTEXT_HMAC_SECRET, CAIPE_ORG_KEY, MCP_SERVICE_OIDC_CLIENT_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes643 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

account_service__can_i

Checks if the current account has permission to perform a specified action on a resource.

account_service__get_account

GetAccount returns an account.

account_service__list_accounts

ListAccounts returns the list of accounts.

application_service__list_resource_events

ListResourceEvents returns a list of event resources.

application_service__list_links

ListLinks returns the list of all application deep links.

application_service__pod_logs

Stream log entries for a specified pod in an ArgoCD application.

list_applications

List applications in ArgoCD with filtering and pagination options

get_application_details

Get details for a specific application

create_application

Construct dependencies and register the Slack request boundary.

update_application

Update an existing application in ArgoCD

delete_application

Delete an application from ArgoCD

sync_application

Sync an application in ArgoCD

version_service__version

Fetches version information of the API server.

project_list

List returns a paginated list of projects.

project_create

Create a new ArgoCD project.

project_delete

Delete a project.

project_get

Get a project.

project_update

Update a project.

application_set_service__generate

Generate an application set service.

applicationset_list

List returns a paginated list of applicationsets.

applicationset_create

Create an application set.

applicationset_service__get

Get an applicationset by name.

applicationset_service__delete

Delete an application set.

certificate_service__list_certificates

List all available repository certificates.

cluster_service__get

Get a cluster by server address.

cluster_service__list

List returns a paginated list of clusters.

search_argocd_resources

Search across ArgoCD resources using two-tier search strategy.

gpg_key_service__get

Get information about a specified GPG public key from the server.

gpg_key_service__list

List all available repository certificates.

gpg_key_service__create

Create one or more GPG public keys in the server's configuration.

gpg_key_service__delete

Delete specified GPG public key from the server's configuration.

aws_cli_execute

Execute an AWS CLI read-only command against a specific AWS account.

eks_kubectl_execute

Execute a kubectl command against an Amazon EKS cluster.

get_entities_by_query

Search for entities by a given query.

get_techdocs_metadata

Retrieves TechDocs metadata for a specific entity to check if documentation exists and get its build status.

get_techdocs_entity_metadata

Retrieves entity-specific TechDocs metadata, including the documentation reference and build information.

get_techdocs_page

Retrieves a specific TechDocs page content for an entity.

get_techdocs_mkdocs_yml

Retrieves the mkdocs.yml configuration for an entity's TechDocs, which contains the documentation structure and navigation.

search_techdocs

Searches across all TechDocs content for the given query.

get_techdocs_index

Retrieves the documentation index/table of contents for an entity's TechDocs.

list_entities_with_techdocs

Lists all entities that have TechDocs documentation available.

get_attachments
get_blog_posts
create_blog_post
get_content_labels
add_labels_to_content
get_pages
create_page
get_spaces
create_space
get_available_space_permissions
get_footer_comments
create_footer_comment
get_inline_comments
create_inline_comment
get_admin_key
enable_admin_key
disable_admin_key
get_attachment_by_id
delete_attachment
get_attachment_labels
get_attachment_operations
get_attachment_content_properties
create_attachment_property
get_attachment_content_properties_by_id
update_attachment_property_by_id
delete_attachment_property_by_id
get_attachment_versions
get_attachment_version_details
get_attachment_comments
get_blog_post_by_id
update_blog_post
delete_blog_post
get_blogpost_attachments
get_custom_content_by_type_in_blog_post
get_blog_post_labels
get_blog_post_like_count
get_blog_post_like_users
get_blogpost_content_properties
create_blogpost_property
get_blogpost_content_properties_by_id
update_blogpost_property_by_id
delete_blogpost_property_by_id
get_blog_post_operations
get_blog_post_versions
get_blog_post_version_details
convert_content_ids_to_content_types
get_custom_content_by_type
create_custom_content
get_custom_content_by_id
update_custom_content
delete_custom_content
get_custom_content_attachments
get_custom_content_comments
get_custom_content_labels
get_custom_content_operations
get_custom_content_content_properties
create_custom_content_property
get_custom_content_content_properties_by_id
update_custom_content_property_by_id

543 further tools are not listed here. The complete surface is in the source.

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configMCP_MODE
configMCP_HOST
configMCP_PORT
configSERVER_NAME
configAWS_CLI_MAX_EXECUTION_TIME
configKUBECTL_MAX_EXECUTION_TIME
configRESTRICT_KUBECTL_SECRETS
configRESTRICT_KUBECTL_PROXY
configRESTRICT_KUBECTL_EXEC
configRESTRICT_KUBECTL_ATTACH
configRESTRICT_KUBECTL_CP
configRESTRICT_KUBECTL_PORT_FORWARD
configAWS_CLI_MAX_OUTPUT_SIZE
configMAX_CONCURRENT_AWS_CALLS
configMAX_CONCURRENT_KUBECTL_CALLS
configAWS_ACCOUNT_LIST
configCROSS_ACCOUNT_ROLE_NAME
configAWS_REGION
configAWS_DEFAULT_REGION
configMCP_JIRA_LOG_LEVEL
configAGENT_NAME
configENABLE_SPLUNK_LOGS
configSCHEDULER_URL
🔐 secretSCHEDULER_SERVICE_TOKEN
configHTTP_TIMEOUT
configWEBEX_INTEGRATION_APP_NAME
configAPP_NAME
configWEBEX_WORKSPACE_ALIAS
configWEBEX_WORKSPACE_ID
configWEBEX_ADMIN_API_ENABLED
configLOG_LEVEL
configHOST
configEXT_AUTHZ_GRPC_BIND
configJWT_JWKS_URL
configJWT_ISSUER
configJWT_AUDIENCES
configJWT_ALGORITHMS
configOPENFGA_BYPASS_SUBS
🔐 secretCAIPE_AGENT_CONTEXT_HMAC_SECRET
configCAIPE_AGENT_CONTEXT_MAX_AGE_SECONDS
configCAIPE_AGENT_CONTEXT_LOCAL_MAX_AGE_SECONDS
🔐 secretCAIPE_ORG_KEY
configCAIPE_RESTRICTED_MCP_SERVERS
configOPENFGA_RELATION
configOPENFGA_OBJECT
configDEV_HOT_RELOAD
configCUSTOM_CA_BUNDLE
configREQUESTS_CA_BUNDLE
configSSL_CERT_FILE
configSSL_VERIFY
configUSE_IMPERSONATION_TOKENS
configMCP_SERVICE_OIDC_CLIENT_ID
configINGESTOR_OIDC_CLIENT_ID
🔐 secretMCP_SERVICE_OIDC_CLIENT_SECRET
configMCP_SERVICE_OIDC_TOKEN_URL
configKEYCLOAK_URL
configKEYCLOAK_REALM
configRAG_MCP_SERVER_IDS
configARGOCD_API_URL
configARGOCD_URL
configMAX_SEARCH_RESULTS
configWARN_SEARCH_RESULTS
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

643/643 tools missing one or more hints — account_service__can_i (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); account_service__get_account (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); account_service__list_accounts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +640 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 51/643 tools referenced in tests (8%)

Write tests that reference each tool by name so every tool has at least one test.

No access to sensitive paths

Reads sensitive paths: ~/.aws

Remove reads of sensitive system paths. If you genuinely need them, document why in the README.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/caipe-io/ai-platform-engineering?variant=verified)](https://m8ven.ai/mcp/caipe-io/ai-platform-engineering)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: d9d9dc4ab51e48ef475657275f77e21c0d92be33
code hash: b61a7e7af4949c82d84dd1e15c059598b3163def40f72744133c256bd078cfca
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client