> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentlinkops.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Give your agent repository context

> Run the separate local MCP host for manual site inputs, imported Search Console rows and cited site facts inside a fixed repository boundary.

Repository context gives your agent manual site inputs, saved search observations and bounded public site facts. These eight tools run on a separate local stdio MCP server. The hosted HTTP MCP endpoint cannot read your repository files.

## Start the local host

Use an authorized checkout with dependencies installed and Node.js 22 or later. Initialize the ledger in the customer repository, then configure your MCP client to launch:

```bash theme={null}
node /path/to/linktrail/cli/context-mcp.js --root /absolute/customer/repository
```

Set the executable to `node` and supply the remaining values as arguments in clients that use a command/argument form. The root is fixed at startup. Tool arguments cannot move it; configured paths and imports must remain inside that boundary, including through symlinks.

## Start from manual context

Call [context\_status](/reference/context/context_status), then [context\_manual](/reference/context/context_manual). `manual_only` is a complete configuration. Record target pages, your offering, assets and approved competitors through the repository's manual inputs. Manual statements remain judgments with their own source label.

Use [context\_focus](/reference/context/context_focus) to select focus pages. It considers manual targets before saved search clicks. For one page, [context\_gsc\_page](/reference/context/context_gsc_page) reads existing fact rows without making a Google request.

## Add dated facts

[context\_gsc\_import](/reference/context/context_gsc_import) accepts a supported connector handoff inside the repository. Preserve its retrieval identity, aggregation and date window. Missing rows in a truncated result never mean zero impressions. A direct [GSC refresh](/reference/context/context_gsc_refresh) needs its own read-only Google access and obeys bounded request limits.

[context\_profile\_build](/reference/context/context_profile_build) fetches a bounded public site profile. Unreadable pages stay explicit. [context\_profile\_check](/reference/context/context_profile_check) checks whether citations in the authored profile resolve to manual inputs or fact rows.

Use the facts in a [campaign brief](/campaign-workflows), keeping observations separate from your agent's conclusions. The [concepts guide](/guides/concepts) explains ownership, and [troubleshooting](/guides/troubleshooting) covers missing grants and path refusals.

Read [local context results](/reference/context/results) for partial refreshes, nullable metrics and missing-file responses.