MCP and agents
obsei mcp serves these tools over stdio:
| Tool | Use |
|---|---|
feedback_stats |
Counts and average rating grouped by source, instance, sentiment, intent, lang (language), rating, route, day, week or month |
search_feedback |
Matching feedback, newest first, as citable evidence |
get_feedback |
One record by id, to verify a citation |
list_themes |
Stable themes with trends (rising as Studio shows it), sources, languages and intents (k-anonymous) |
propose_issue |
Queue an issue for a person to approve (only when a GitHub, Jira or Linear sink is configured) |
Results contain redacted text, labels, source, time and record id. They never contain author
pseudonyms. The server also offers a voc_report prompt. Its initialize handshake negotiates
MCP protocol 2024-11-05 to 2025-11-25 (a client offering 2026-07-28 gets 2025-11-25); the
bundled MCP SDK also answers 2026-07-28 requests that carry their version in _meta. Every tool
declares readOnlyHint, destructiveHint and openWorldHint: the four read tools are
read-only, and propose_issue writes only to obsei’s own queue.
Untrusted text
Section titled “Untrusted text”Each evidence item’s text is what a customer wrote, and anyone can write a review. Items carry
"untrusted": true, and the tool descriptions and server instructions tell agents to quote that
text and never follow instructions in it. Theme labels and descriptions are written by a model
from that text, so treat them the same way.
Approvals
Section titled “Approvals”An agent cannot act outside obsei. propose_issue(target, title, body, record_ids) stores a
pending approval and returns its id; nothing is sent. target is the key of a github_issues,
jira or linear sink in obsei.yaml (the tool description lists them; a key that names
different sinks in several pipelines becomes pipeline/key). Cited record ids must exist.
A person then decides, with the CLI or, as admin, over HTTP:
obsei approvals list --status pendingobsei approvals show apr_... # the proposal and the exact issue textobsei approvals approve apr_... --by anaobsei approvals reject apr_... --by ana --reason "duplicate of #12"Approving opens the issue with that sink’s settings. The issue starts with “Proposed by an AI agent via obsei; review before acting” and lists the cited records. An approval is carried out once: approving it again is refused, and if opening the issue failed you can approve it again without risking a second issue, because the sink first looks for one tagged with the approval id. Every proposal and decision is written to the audit log.
Over stdio, obsei mcp opens the store read-only, and read-write only for the moment it stores
a proposal. DuckDB allows one writer, so while obsei serve or obsei run holds the store,
send proposals through obsei serve’s /mcp instead.
The rule behind this: fixed labels from a classifier may pick routes on their own, but any free text an agent writes after reading feedback goes through a person, because private data, untrusted content and a way to send messages out together are what a prompt injection needs.
Claude Code
Section titled “Claude Code”/plugin marketplace add obsei/obsei/plugin install obsei@obseiThis installs from obsei’s own marketplace in the GitHub repository; obsei isn’t in Claude’s
official plugin directory yet. The plugin adds the MCP server and a voice-of-customer skill. Codex, Copilot, VS Code, Cursor,
Gemini and other tools: see Use obsei from your AI tool.
Claude Desktop and other clients
Section titled “Claude Desktop and other clients”{ "mcpServers": { "obsei": { "command": "uvx", "args": ["--from", "obsei>=1.0", "obsei", "mcp"], "env": { "OBSEI_DB": "/path/to/obsei.duckdb", "OBSEI_DB_KEY": "..." } } }}Remote MCP
Section titled “Remote MCP”obsei serve exposes the same tools at /mcp (streamable HTTP). Set OBSEI_API_TOKEN; clients
send Authorization: Bearer <token>. Put it behind your SSO proxy for per-user access. Give
agents an analyst token: proposals then record who made them (agent:<user>), and only admins
can approve them.