MCP server
Ask your assistant what AI says about you
Connect ModelSaid to the assistant you already use, and your visibility data is just there: scores, competitors, what changed this week. No dashboard, no copying numbers into a chat window.
Your API token
Paste a token and every snippet below fills in with it, ready to copy. This happens in your browser: the token is never sent to us, never put in the address bar, and never saved. Create one in your dashboard, under API tokens.
Snippets show a placeholder until you paste a token.
Where Run this in your terminal
claude mcp add --transport http modelsaid https://api.modelsaid.com/mcp \
--header "Authorization: Bearer msk_your_token_here"Add --scope user to make it available in every project rather than just this one.
Official docs: Claude Code
What your assistant can do
This table is generated from the same list the server enforces, so it cannot show you a tool that does not exist or put one on the wrong plan.
| Tool | What it does | Plan | Scope |
|---|---|---|---|
list_projects | List the businesses in your account with their latest visibility score. | Monitor | projects:read |
get_project | Get one business: its details, latest score and when it is next scanned. | Monitor | projects:read |
compare_projects | Compare visibility scores across every business in the account. | Monitor | projects:read |
create_projectWrites | Create a project (a business to track). An account with an active subscription gets its first scan started immediately. | Monitor | scans:write |
get_account_usage | What the account has used of its plan this month: projects, on-demand scans and Auto Fix runs, with a per-project breakdown. | Monitor | projects:read |
get_project_slots | How many project slots the account pays for, and how many are in use. | Monitor | projects:read |
get_latest_report | The most recent visibility report for a business, including score components. | Monitor | reports:read |
list_competitors | Competitors the models named instead of, or alongside, this business. | Monitor | reports:read |
get_trend | Score history over time, bounded by the plan trend retention. | Monitor | reports:read |
export_report | A full report rendered as Markdown, ready to paste into a deliverable. | Monitor | reports:read |
list_model_answers | The verbatim answers each model gave, per prompt. The underlying evidence. | Monitor | reports:read |
get_accuracy_findings | Factual inaccuracies the fact-check found in model answers about this business. | Monitor | reports:read |
get_facts | The ground-truth facts the accuracy check measures model answers against. | Monitor | reports:read |
update_factsWrites | Correct ground-truth facts. Only the fields you name change; the rest are kept. | Monitor | config:write |
get_unified_report | One project measured, in one call: latest report, snapshot, score trend and share of voice. | Monitor | reports:read |
get_readiness | The technical AI-readiness scorecard for a business website. | Monitor | reports:read |
list_changes | Recent monitoring changes and alerts for a business. | Monitor | reports:read |
list_technical_history | Past technical checks for a business: readiness, PageSpeed and availability. | Monitor | reports:read |
list_issues | Open issues for a business, ranked by severity decayed over recency. | Monitor | reports:read |
get_monitoring_config | Whether visibility and technical monitoring are on, how often, and the plan caps. | Monitor | projects:read |
set_monitoring_configWrites | Turn visibility or technical monitoring on or off, and set cadence and extra pages. | Monitor | config:write |
list_alert_rules | The custom alert rules on a business, with the plan cap and how many are used. | Monitor | projects:read |
create_alert_ruleWrites | Add a custom alert rule watching one metric against a threshold. | Monitor | config:write |
update_alert_ruleWrites | Change an existing alert rule. Only the fields you name change. | Monitor | config:write |
delete_alert_ruleWrites | Remove a custom alert rule. | Monitor | config:write |
list_alert_channels | Where this account delivers alerts. Requires a token covering all projects. | Monitor | projects:read |
create_alert_channelWrites | Add an email or https webhook destination for alerts. Requires a token covering all projects. | Monitor | share:write |
delete_alert_channelWrites | Remove an alert destination. Requires a token covering all projects. | Monitor | config:write |
list_content_briefs | Content opportunities computed from the latest scan. | Monitor | content:read |
get_content_draft | One content draft with its AEO score and guardrail flags. | Monitor | content:read |
create_content_draftWrites | Generate a content draft. Consumes one draft from the monthly quota. | Monitor | content:write |
get_brand_profile | The brand guardrails drafts are generated and validated under. | Monitor | content:read |
set_brand_profileWrites | Update the brand guardrails profile. Only the fields you name change. | Monitor | config:write |
refresh_content_briefsWrites | Recompute content opportunities from the latest finished scan. No AI spend. | Monitor | content:write |
dismiss_content_briefWrites | Dismiss a content opportunity. No later refresh brings it back. | Monitor | content:write |
list_content_drafts | The drafts for a business, newest first, with the monthly quota used and its cap. | Monitor | content:read |
update_content_draftWrites | Edit a draft title or body, or approve a flagged draft. Edits are re-checked against the guardrails. | Monitor | content:write |
run_scanWrites | Start a visibility scan. Consumes one on-demand scan from the monthly quota. | Monitor | scans:write |
list_scans | Scan history for a project: every scan with its status, score and timing. | Monitor | reports:read |
get_scan | One finished scan: status, score and score components. Omit scan_id for the most recent. | Monitor | reports:read |
run_auto_fixWrites | Propose AEO fixes as a pull request on the connected repository. Never writes the default branch. Blocks for several minutes. | Agency Pro | autofix:write |
analyze_repositoryWrites | Investigate the connected repository and return file-level AEO recommendations. SPENDS MONEY: roughly USD 0.03 to 0.75 of the account's shared monthly AI budget, and one Auto Fix run against its daily and monthly allowance, unless a cached investigation of the same commit makes the call free. Two calls, always: the first one omits confirm_token, spends nothing, and returns the price and what the account has left for you to put to your human before you call again. | Agency Pro | autofix:write |
list_custom_prompts | The custom prompts this business is measured on, with the enabled cap and usage. | Monitor | projects:read |
create_custom_promptWrites | Add a custom prompt for the next scans to ask. Starts enabled, within the plan cap. | Monitor | config:write |
update_custom_promptWrites | Change or enable a custom prompt. Only the fields you name change. | Monitor | config:write |
delete_custom_promptWrites | Remove a custom prompt. Answers already collected with it are kept. | Monitor | config:write |
get_prompt_suggestions | Prompts worth tracking, mined from Search Console queries and industry templates. | Monitor | reports:read |
get_share_of_voice | Own versus competitor share of AI answer mentions over time, in a date window. | Monitor | reports:read |
get_roi | The stored revenue-at-stake assumptions and the estimate they produce. | Monitor | projects:read |
set_roi_inputsWrites | Replace the revenue-at-stake assumptions. All fields at once, as on the dashboard. | Monitor | config:write |
get_google_connection | Whether Search Console and GA4 are connected for a project, and which properties are selected. | Monitor | projects:read |
list_google_properties | The Search Console sites and GA4 properties the connected Google account can see. | Monitor | projects:read |
select_google_propertiesWrites | Choose which Search Console site and GA4 property feed this project. Only the ones you name change. | Monitor | config:write |
disconnect_googleWrites | Disconnect Google from a project, deleting the stored tokens and the synced daily rows. | Monitor | config:write |
get_search_console_daily | Daily Search Console clicks and impressions per query, from the connected site. | Monitor | reports:read |
get_ga4_daily | Daily GA4 sessions and conversions per channel, from the connected property. | Monitor | reports:read |
get_github_connection | Whether this project has a repository bound, and how many GitHub App installations the account holds. | Monitor | projects:read |
list_github_repos | The repositories every GitHub App installation on this account can reach. | Agency Pro | projects:read |
select_github_repoWrites | Bind one repository to this project. Auto Fix runs read and target it. | Agency Pro | config:write |
list_github_branches | The branches of the repository bound to this project, and the current base branch. | Agency Pro | projects:read |
set_github_base_branchWrites | Choose the branch Auto Fix runs are based on. Verified against the repository before it is stored. | Agency Pro | config:write |
disconnect_github_repoWrites | Unbind this project from its repository. Other projects and the App installation are untouched. | Agency Pro | config:write |
create_share_linkWrites | Publish one finished scan report at a public link that anyone holding the URL can read without signing in. | Monitor | share:write |
list_share_links | The share links this account has published, with their public URLs, status, and how many active links each project has left. | Monitor | projects:read |
revoke_share_linkWrites | Revoke a share link so its public page and badge stop resolving. | Monitor | config:write |
get_white_label_profile | The white-label branding for shared and exported reports, and whether the plan includes it. Requires a token covering all projects. | Monitor | projects:read |
update_white_label_profileWrites | Change the white-label branding on shared and exported reports. Only the fields you name change. Requires a token covering all projects. | Monitor | config:write |
Available on Monitor, Agency, Agency Pro. Your assistant only sees the tools your plan and your token allow, so there is nothing to configure and nothing to accidentally call.
What a token can and cannot do
- You choose the scopes
- A token only carries what you tick. A read-only token cannot start a scan or open a pull request, whatever the assistant decides to try.
- Your plan is checked every call
- Not stored in the token. If a subscription lapses, the paid tools stop working on the very next request rather than whenever a token expires.
- Every call is recorded
- Which token, which tool, which project, and what happened. Arguments are not stored, so we do not keep a second copy of your business data.
- Revoking is immediate
- Revoke a token and the next call fails. There is no cached session to wait out and no refresh token still in flight.
The MCP server is on every paid plan
Monitor gets your own projects and reports. Agency adds work across clients. Agency Pro adds the raw model answers and lets an assistant open fix pull requests for you.