Skip to main content

MCP

COBACK speaks the Model Context Protocol, so Claude (and any MCP client) can work your workspace directly. The endpoint is stateless streamable HTTP; one command connects it:

claude mcp add --transport http coback https://api.coback.ai/api/v1/mcp \
  --header "Authorization: Bearer $COBACK_API_KEY"

The dashboard shows this exact command, filled in, when you create a key under Settings. With the CLI installed, coback mcp prints it too.

Tools

Read tools, on every key:

ToolDoes
search_brainSemantic search over the company brain; the answer to "how does the company handle X"
list_cards / get_cardEnumerate knowledge cards; fetch one with full content
get_skills_fileThe entire brain as one markdown file
search_corpusSemantic search over the uploaded documents
list_lawsRecently ingested laws, filterable by jurisdiction and date
list_matchesScreening results with score, rationale, and verdict
list_tasksThe task board, filterable by status
list_products / get_productProduct compliance state and findings

Write tools, only on read-and-write keys (a read key does not even see them):

ToolDoes
submit_match_feedbackRecord a relevance verdict on a screening result
create_task / update_task_statusPut work on the board, move it
add_commentComment on a task or match, attributed to the key

Notes

  • The endpoint keeps no session: every POST is one JSON-RPC message, answered as JSON.
  • Tool output is markdown text, so any client can render it without a schema.
  • Trust labels travel with the content: brain cards state whether a human verified them, and screening results carry the engine's written rationale.
  • The same rate limit as the REST API applies: 120 requests per minute per key.