Claude connector
Connect Claude to your Elixion workspace — find work, understand it, and file new work, acting as you.
Claude connector
Connect Claude to Elixion so it can find your work, understand it, and file new work — acting as you, with exactly the permissions your Elixion account already has.
- Connector URL:
https://api.elixion.ai/mcp - Authentication: OAuth 2.1 with PKCE. Claude sends you to Elixion to sign in and approve.
- Cost: nothing beyond your existing Elixion plan.
Works anywhere Claude supports custom connectors — claude.ai, Claude Cowork and Claude Desktop all use the same connection.
Connect it
- In Claude, open Settings → Connectors → Add custom connector.
- Paste the URL:
https://api.elixion.ai/mcp - Click Connect. Claude sends you to Elixion.
- Sign in if you aren't already, then choose the workspace this connection should use by default, and approve.
- Claude shows the connector as Connected.
Permissions
At the approval step Claude asks for one or both of:
| Scope | What it allows |
|---|---|
| elixion:read | Read projects, issues, boards and sprints you can already see |
| elixion:write | Create and update issues, comment, assign, and manage sprints |
A connection approved with read access only cannot write — the write tools refuse the call and say so.
Changing the default workspace
The workspace you choose at approval becomes the connection's default. To change it, reconnect the connector and pick a different one.
Disconnecting
Remove the connector in Claude, or revoke the connection from Elixion. Either one takes effect immediately: the next call fails and Claude asks you to reconnect.
What Claude can do
Claude acts as you. It cannot see a project you can't see, and it cannot do anything in Elixion you couldn't do yourself.
Reading
| Tool | What it's for |
|---|---|
| whoami | Who Claude is connected as — what makes "assign this to me" work |
| list_projects, get_project | Find a project and see who's on it |
| list_project_members | Who's on the team — what makes "assign this to Sarah" work |
| list_issues | "What's on my plate", "what's open in ELI" |
| get_issue | One issue: description, subtasks, comments. full=true for long text |
| list_issue_comments | A whole comment thread, a page at a time, uncut |
| search_issues | Anything the simple filters can't express, using EQL |
| get_board | The board as it appears on screen |
| list_sprints, get_sprint | Sprint dates, goal, status, capacity |
| get_issue_relationships | What blocks an issue, what it blocks, duplicates |
| list_issue_history | What changed on a ticket, and who changed it |
| list_issue_worklogs | Time logged against an issue |
| list_epics | Epics with progress: how many issues and points are done |
| get_sprint_analytics | How a sprint is tracking, including mid-sprint scope change |
| get_project_velocity | Points delivered per completed sprint, and the average |
| list_notifications | What needs your attention in the connected workspace |
| list_milestones, get_milestone | Upcoming releases and checkpoints, with progress |
| list_milestone_issues | What's in a milestone — and what's blocking it |
| list_documents, get_document | Find and read project docs: PRDs, specs, notes |
| get_time_report | Time logged across a project or period, broken down by person |
| get_timesheet | A timesheet — your own, or a teammate's where you share a project |
| get_capacity_planning | Who has bandwidth for the sprint, and who's overloaded |
| list_agents | The AI agents working on your projects |
| list_agent_runs | What the agents have been doing, and whether runs finished |
| get_issue_agent_output | An agent's progress and output on one issue |
| list_issue_templates, get_issue_template | Your team's issue patterns, ready to apply when filing |
| list_recurring_tasks | Scheduled recurring tasks and when they run next |
| get_eql_help | The exact EQL grammar the search understands |
| get_project_activity_feed | What happened on a project — the standup rundown |
Writing
These change your workspace, and other people see the result. Claude asks you before using them.
| Tool | What it's for |
|---|---|
| create_issue | File a new issue |
| update_issue | Change title, priority, points, labels or description |
| append_to_issue_description | Add to the end of a description without rewriting it |
| transition_issue_status | Move an issue between statuses |
| assign_issue | Put an issue on someone's plate |
| add_issue_comment | Comment, attributed to you |
| manage_sprint | Create, start, complete or cancel a sprint |
| manage_sprint_issues | Add issues to a sprint, or take them out |
| manage_issue_link | Link issues — "ELI-10 is blocked by ELI-9" — or unlink |
| add_work_log | Log time spent on an issue |
| mark_notifications_read | Clear notifications in the connected workspace |
| create_milestone | Add a release or checkpoint with a target date |
| manage_milestone | Update, complete or reopen a milestone — no delete |
| manage_milestone_issues | Put issues into a milestone, or take them out |
| create_document | File a document — a PRD Claude drafted, meeting notes |
| manage_issue_archive | Archive finished issues, or bring them back |
| manage_bulk_issues | Transition, assign, label or update up to 50 issues in one call |
Long descriptions and comment threads
Tool results are bounded, because a result that overflows takes the answer down with it. The limits, and how to get past each one:
| What | Default | How to get the whole thing |
|---|---|---|
| Description, acceptance criteria | 4,000 characters | get_issue(full=true) — raises the cap to 100,000 |
| A comment inside get_issue | 500 characters | list_issue_comments returns bodies uncut |
| Comments inside get_issue | The latest 5 | list_issue_comments pages through all of them |
Truncation is never silent. Any clipped field comes back with
truncated: true and a visible … [truncated] marker, so Claude can tell you
text is missing instead of presenting a partial spec as the whole one. If you
do not see that flag, you have everything.
Amending a long description. Do not read a description and write it back to
add a paragraph — if the read was truncated, the rewrite destroys the tail you
never saw. Use append_to_issue_description, which adds to the end without
needing to read it at all. Reach for update_issue only when you genuinely mean
to replace the text, and read it with full=true first when you do.
Things the connector deliberately will not do
These are refusals by design, not gaps.
It cannot mark an issue TESTING or DONE. Acceptance belongs to the issue's
reporter, so the connector stops at IN_REVIEW. Ask Claude to close something
and it will tell you to do it yourself rather than pretend it did.
It cannot delete a sprint. cancel is the only teardown, so a sprint's
history is never destroyed.
It will not silently overwrite a rich description. If an issue's description contains formatting, images or @-mentions, the connector refuses to replace it with plain text until you have seen what would be lost and confirmed.
It cannot delete anything. There is no tool to delete an issue, a sprint, a project, a milestone, a document, a comment or a work log — not because the platform can't, but because the connector deliberately does not expose it. The only things it can remove are a link between two issues and an issue's membership in a sprint or milestone; archiving an issue is always reversible.
It cannot reach outside the workspace you connected. The grant is bound to one workspace at consent. Notifications, issues and analytics from your other workspaces are not visible to it, and it will not mark them read.
Try it
- "What's assigned to me in Elixion right now?"
- "Show me the ELI board — what's blocked?"
- "Find issues that aren't done and are due this week."
- "Read ELI-1239 and summarise what's left."
- "File a bug in ELI: the export button 404s on Safari."
Troubleshooting
Claude says it needs me to reconnect. The connection expired or was revoked. Reconnect in Settings → Connectors.
Claude can't see a project I expect. The connector inherits your Elixion permissions exactly. If you can't open the project in Elixion, Claude can't either — ask a workspace admin to add you.
Claude says it can't write. The connection was approved with read access only. Reconnect and approve write access.
A call failed with a rate-limit error. Each connection has its own request budget. Wait for the window given in the error and retry. If it keeps happening in normal use, contact us — the limits are meant to be invisible.
Privacy
Claude reads only what you ask it to, using your own Elixion permissions, and
Elixion never receives your Claude conversation. Access tokens are stored hashed;
tokens, authorization codes and Authorization headers are never logged.
Full detail: Privacy Policy.