Stride

Hosted MCP server with OAuth sign-in, and plugins for Claude Code, Codex and Cursor: coding agents read each story's acceptance criteria, designs and tests from Stride and update it as they work.

View on stride.page

Hosted MCP Server

npx add-mcp 'https://www.stride.page/api/mcp/stride'

Installs into Claude Code, Codex, Cursor and more

Documentation

Stride is a backlog MCP server for Claude Code. It exposes your backlog over the Model Context Protocol (MCP), so Claude Code reads and writes real stories, sprints, tests, and architecture decisions, working from your connected delivery graph instead of code pasted into a chat window. Codex and Cursor connect to the same server.

Why your AI agent needs your backlog

A coding agent is only as good as the context it can see. Point it at the repo alone and it writes plausible code for the wrong requirement. Stride gives the agent the structured context it’s missing (acceptance criteria, the linked test cases, the architecture decision that constrains the change, the sibling stories in the sprint) so it ships the feature you actually scoped, not just code that compiles.

How to connect it

Sign in with your Stride account and there is nothing to copy. For CI and other runs that cannot open a browser, use an agent key instead.

Sign in with your Stride account

Add Stride to Claude Code: claude mcp add --transport http stride https://www.stride.page/api/mcp/stride. Put --scope user after stride to use it in every project.
In Claude Code, run /mcp, select stride and choose Authenticate. Your browser opens to Stride.
Sign in, choose the project the agent works in and the projects it can reach, and click Allow. You can disconnect it at any time in Settings → Integrations → Connected apps.

Or install the Stride plugin: /stride:next and /stride:done

The plugin adds the same server and two commands. /stride:next picks up your next story (the one a teammate staged for you, or the top one assigned to you) with its full spec and starts it. /stride:done checks the work against the story’s acceptance criteria and moves it to In Review.

claude plugin marketplace add Newlight-Solutions/stride-plugins
claude plugin install stride@stride

Then run /mcp, select plugin:stride:stride and choose Authenticate.

Or use an agent key

In Stride, open Settings → Integrations → Claude Code, pick the project the agent should reach, and click Generate Agent Key.
Put the key in an environment variable: export STRIDE_AGENT_KEY="nl_your_agent_key" on macOS and Linux, or setx STRIDE_AGENT_KEY "nl_your_agent_key" on Windows, then open a new terminal. The config below refers to the variable, so the key never sits in a file you might commit.
Paste the config into .mcp.json at your repository root to share the server with the project. Claude Code asks you to approve a project server the first time it loads it.

{
  "mcpServers": {
    "stride": {
      "type": "http",
      "url": "https://www.stride.page/api/mcp/stride",
      "headers": {
        "Authorization": "Bearer ${STRIDE_AGENT_KEY}"
      }
    }
  }
}

To use Stride in every project instead, add it once from your terminal: claude mcp add --transport http stride --scope user https://www.stride.page/api/mcp/stride --header "Authorization: Bearer $STRIDE_AGENT_KEY" (in PowerShell, write $env:STRIDE_AGENT_KEY). The shell fills in the key, so Claude Code stores it in ~/.claude.json.

Then run claude mcp list: Stride should show as connected, and /mcp inside Claude Code shows its tool count. Claude Code discovers Stride’s tools automatically over MCP. Codex and Cursor work the same way — switch tabs above for the same endpoint in their own format.

What the agent can do

Stride exposes 131 RBAC-gated tools across all four modules. Every call is permission-checked by the dispatcher before it runs, and every write lands in the audit log as via: "mcp".

Module	Representative tools
Plan	read a story’s full spec in one call (acceptance criteria, designs, docs, tests); create / update / search stories, epics, sprints, releases; bulk-update; open a GitHub draft PR from a story
Verify	create test cases, fetch test runs, rerun failed tests, run quality-gate checks, get defects
Design	read architecture diagrams (ERD, BPMN, C4 levels) and link them to stories; create / update / search documents and ADRs, append to a document
Optimize	get processes, list process insights, read delivery KPIs
Workspace	list members, manage labels, attachments, reactions, end session

Good to know

131 tools don’t crowd the context. Claude Code’s tool search is on by default: a session starts with only the tool names, and a tool’s full definition loads when Claude needs it. Claude Code sets no per-server tool limit.
Pre-approve the tools you trust. Claude Code asks before using an MCP tool. Stride’s tools appear as mcp__stride__stride_<tool>, so the permission rule mcp__stride__* allows them all, while mcp__stride__stride_get_* and mcp__stride__stride_list_* allow only tools that read. Tools the plugin added start with mcp__plugin_stride_stride__ instead.
If Stride shows as needing authentication, run /mcp and choose Authenticate. With an agent key, a failed server usually means STRIDE_AGENT_KEY was not set in the terminal Claude Code started from; claude mcp list warns about the missing variable.
A CI runner needs a key. It cannot open a browser to sign in, so give it an agent key in the Authorization header.
No timeout to configure. Claude Code gives each request to a remote MCP server 60 seconds by default. Stride answers within that, and long generations such as a diagram carry on in the background, where the agent can check on them.

Checked against Claude Code’s documentation on October 24, 2026.

Frequently asked questions

How do I connect Claude Code to Stride?

Run claude mcp add --transport http stride https://www.stride.page/api/mcp/stride, then in Claude Code run /mcp, select stride and choose Authenticate. You sign in to Stride in your browser, choose the project the agent works in, and allow it, so there is no key to copy. Or install the Stride plugin, which adds the same server plus /stride:next and /stride:done. For CI and other runs that cannot open a browser, generate an agent key in Settings → Integrations → Claude Code and send it as a bearer token instead.

Will 131 tools fill up Claude Code’s context?

No. Claude Code’s tool search is on by default, so only tool names load when a session starts, and a tool’s full definition loads when Claude needs it. Claude Code sets no per-server tool limit; the practical limit is your context window.

Does Stride work with Codex and Cursor too?

Yes. All three use the same MCP endpoint and sign in to Stride the same way; only the setup differs. Claude Code uses JSON, Codex uses TOML, and Cursor uses its own mcp.json. With an agent key instead, Cursor’s Authorization header must use its ${env:NAME} interpolation rather than the bare ${NAME} form. The Stride plugin is packaged for all three.

Is the MCP access permission-scoped?

Every MCP tool call is RBAC-gated by Stride’s dispatcher before the handler runs. Agent keys carry an explicit project scope and an optional max-role cap; an app you sign in gets the projects you chose when you allowed it. The agent acts with your permissions in each project, and every action is recorded in the audit log as via: "mcp".

What can the agent actually do?

Read and write stories, epics, sprints, releases, test cases, defects, documents, and ADRs, and query cross-module context like which open defects block a release. The agent works from your connected delivery graph instead of pasted snippets.

Which plan includes the MCP server?

Every paid plan includes MCP access, the public API, and webhooks. Starter includes one API or agent key and one webhook; Pro and Enterprise increase those limits. An app you sign in uses one agent key. See the pricing page for the full breakdown.

Create a workspace, then sign in from Claude Code to connect it to the delivery record.

Get started

Other integrations

Defined in our glossary