Manage your directory listing changedconnectors/building/managing-your-listing
Nearest release: v2.1.283, published under an hour after upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 25 Sep 2026 18:00 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 25 Sep 2026 18:07 UTC.
Upstream edited
Recorded here
Lines+39added
Lines−33removed
From line
1
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits2to this page, all time
# Manage your directory listing ### Review what the metrics cover ## Next steps # Managing your directory listing ### What the metrics cover
The whole hunk
from line 1, old and new numbered
/
from line 1
1# Managing your directory listing
1# Manage your directory listing
22
3> Track submissions, monitor server health and usage metrics, and edit your Connectors Directory listing
3> Track submissions, monitor server health and usage metrics, and edit your directory listing
44
5Organizations that submit to the [Connectors Directory](/docs/connectors/directory) get a submissions dashboard in Claude.ai at [Organization settings > Directory](https://claude.ai/admin-settings/directory/submissions). Use it to track submissions through review, monitor your published server's health and usage, and edit your listing.
5Organizations that submit a connector to the [directory](/docs/connectors/directory) get a submissions dashboard in the developer portal at [claude.ai/directory/manage](https://claude.ai/directory/manage). This page is for connector authors who have already [submitted a connector](/docs/connectors/building/submission). Use the dashboard to [track a submission through review](#track-submission-status), [monitor your published server's health and usage](#server-health-and-usage-metrics), and [edit your listing](#edit-your-listing).
66
77<Note>
8 The dashboard covers directory-listed remote MCP servers only. Custom connectors and local servers (desktop extensions) don't appear here, and the dashboard shows only your own organization's submissions.
8 This page covers directory-listed remote MCP servers. The dashboard shows only your own organization's submissions. Custom connectors and local servers packaged as desktop extensions don't appear here.
99</Note>
1010
1111## Access the dashboard
1212
13The dashboard is part of your organization's admin settings, so you need:
13The dashboard uses the same access as submitting. [Who can submit to the directory](/docs/directory/publish#confirm-you-can-submit-to-the-directory) lists the plan and role requirements. That access covers everything on this page: viewing submissions, metrics, and reviewer feedback, and editing and submitting listings.
1414
15* **A Team or Enterprise organization**
16* **Directory management access.** By default, only organization Owners and Primary owners have it. On Enterprise, an Owner can delegate access through a custom role with the **Directory** or **Libraries** permission; see [Before you start](/docs/connectors/building/submission#before-you-start) for the steps. Team plans don't have custom roles, so on Team this stays with Owners.
17
18The same access covers everything on this page: viewing submissions, metrics, and reviewer feedback, and editing and submitting listings.
19
2015## Track submission status
2116
22The dashboard lists each of your organization's submissions with its current status. Open a submission to see its full details and any reviewer feedback. When reviewers request changes, their feedback appears on the submission's detail page; address it and resubmit from the same page.
17The dashboard lists each of your organization's submissions with its current status. [Track your submission](/docs/directory/submission-status#mcp-connector-statuses) says what each status means and who acts next. Open a submission to see its full details and any reviewer feedback. When reviewers request changes, their feedback appears on the submission's detail page, where you address it and resubmit.
2318
19A published connector is listed with the **Community** label by default. [Connector verification](/docs/connectors/verification#list-your-own-connector) explains how a listing becomes Verified.
20
2421## Server health and usage metrics
2522
23Once your server is published, its **Overview** and **Usage** tabs in the developer portal show a health badge, topline usage numbers, an error breakdown, and usage by product and by tool.
24
2625<Note>
2726 Metrics are in beta. They're computed daily from directory usage and can lag by up to 24 hours. Time windows with fewer than 5 calls, per-tool rows with fewer than 5 calls, and per-product rows with fewer than 50 calls are omitted.
2827</Note>
2928
30Once your server is published, its detail page shows health and usage data.
29### Review what the metrics cover
3130
32### What the metrics cover
31All of the metrics on this page measure traffic from Claude: claude.ai, Claude Desktop, Claude Code, and other Claude surfaces. Connections that people make to your server from other MCP clients, and local servers that run on a user's own machine, aren't visible to Anthropic and aren't counted. Your own server logs can therefore show activity that this page doesn't.
3332
34All of the metrics on this page measure traffic from Claude: Claude.ai, Claude Desktop, Claude Code, and other Claude surfaces. Connections that people make to your server from other MCP clients, and local servers that run on a user's own machine, aren't visible to Anthropic and aren't counted. Your own server logs can therefore show activity that this page doesn't.
33Tool call totals, error rates, and latency are measured at Anthropic's HTTP connector proxy. The **Used a tool** count and directory rank are measured from the MCP message stream, which covers both the HTTP and legacy WebSocket transports. If users reach your server only over the legacy WebSocket transport, you'll still see the **Used a tool** count and a directory rank, but no tool call totals, error rates, or latency data.
3534
36Tool call totals, error rates, and latency are measured at Anthropic's HTTP connector proxy. Tool call users and directory rank are measured from the MCP message stream, which covers both the HTTP and legacy WebSocket transports. If users reach your server only over the legacy WebSocket transport, you'll still see tool call users and a directory rank, but no tool call totals, error rates, or latency data.
37
3835### Health
3936
40The health badge summarizes your server's recent reliability:
37The health badge summarizes your server's recent reliability as one of these statuses:
4138
42| Status | Meaning |
43| --------------- | ------------------------------------------------------------------------------------------------------------ |
44| **Healthy** | The 30-day disconnect rate is at or below 5% |
45| **Degraded** | The 30-day disconnect rate is above 5% |
46| **Collecting…** | The server is published, but there isn't enough data yet to compute a disconnect rate (metrics update daily) |
47| **Not live** | The server isn't published yet; health appears after publication |
39| Status | Meaning |
40| ------------------- | -------------------------------------------------------------------- |
41| **Healthy** | Request errors are 2% or less of tool calls in the last 30 days |
42| **Worth a look** | Request errors are above 2% |
43| **Degraded** | Request errors are above 5% |
44| **Not enough data** | Request errors haven't been measured yet; metrics update daily |
45| **Not live** | The server isn't published yet, and health appears after publication |
4846
49The disconnect rate is measured against every distinct Claude account that sent your server any MCP message in the last 30 days, including connection attempts that never completed: it is the share of those accounts that chose to disconnect your connector during those 30 days.
47Request errors include tool calls rejected for authentication problems and exclude errors a tool returns in its own result.
5048
5149### Topline metrics
5250
53* **Directory rank**: your position among published directory servers, highest first, ranked by the number of distinct Claude accounts that sent your server any MCP message in the last 30 days. Every MCP message counts toward the ranking, including `initialize` and `tools/list`, and it includes accounts whose connection attempt never finished authenticating — a broader population than the Tool call users card below. A "Trending" tag marks servers in the top 10 by recent growth in that same message-based count.
54* **Tool call users (30d)**: the number of distinct Claude accounts that made at least one tool call (`tools/call`) to your server in the last 30 days. Accounts that only attempted to connect, or connected and browsed your tools without calling one, aren't counted. This card was previously labeled "Active users (30d)" and counted every MCP message, including handshakes from connection attempts that never completed; the renamed metric counts only accounts that actually used your tools, so it is usually much smaller than the number the old card showed.
55* **Tool calls (30d)**: the number of `tools/call` requests Anthropic received for your server in the last 30 days. Protocol messages such as `initialize` and `tools/list` aren't counted here. This is a count of requests, not of users, so retries are included, as are requests that were turned away for authentication problems.
56* **Error rate (30d)**: of the tool calls above, the fraction that either failed at the request level (for example, with a 5xx response or a timeout) or returned an MCP tool result with `isError: true`. Tool-call requests that were turned away for authentication problems aren't counted as errors, but they are included in the total number of tool calls that the rate is measured against. Shown with the most common error types.
51The topline metric cards summarize your server's reach, usage, and reliability over the last 30 days:
5752
53* **Directory rank**: your position among published directory servers, highest first, ranked by the number of distinct Claude accounts that sent your server any MCP message in the last 30 days. Every MCP message counts toward the ranking, including `initialize` and `tools/list`, and it includes accounts whose connection attempt never finished authenticating, which is a broader population than the **Used a tool** card counts. A **Trending** tag marks servers in the top 10 by recent growth in that same message-based count
54* **Used a tool**: the number of distinct Claude accounts that made at least one tool call (`tools/call`) to your server in the last 30 days. Accounts that only attempted to connect, or connected and browsed your tools without calling one, aren't counted. The renamed metric counts only accounts that actually used your tools, so it's usually much smaller than the number the old card showed
55* **Tool calls (30d)**: the number of `tools/call` requests Anthropic received for your server in the last 30 days. Protocol messages such as `initialize` and `tools/list` aren't counted here. This is a count of requests, not of users, so retries are included, as are requests that were turned away for authentication problems
56* **Error rate (30d)**: of those tool calls, the fraction that either failed at the request level, for example with a 5xx response or a timeout, or returned an MCP tool result with `isError: true`. Tool-call requests that were turned away for authentication problems aren't counted as errors, but they are included in the total number of tool calls that the rate is measured against. Shown with the most common error types
57
5858### Error breakdown
5959
6060A table breaks errors out over 1-day, 7-day, and 30-day windows: total calls, overall error rate, tool versus request error rates, HTTP 4xx and 5xx rates, and the top error types in each window.
from line 61
6161
6262### Usage by product
6363
64A per-product table shows 7-day calls, error rate, and p50/p95/p99 latency, broken down by the Claude product the calls came from, such as Claude.ai, Claude Desktop, Claude Code, and Cowork. Only a fixed set of Claude surfaces is shown, and Anthropic's own internal monitoring traffic is excluded.
64A per-product table shows 7-day calls, error rate, and p50/p95/p99 latency, broken down by the Claude product the calls came from, such as claude.ai, Claude Desktop, Claude Code, and Cowork. Only a fixed set of Claude surfaces is shown, and Anthropic's own internal monitoring traffic is excluded.
6565
66Because this table covers a shorter window, drops low-volume rows, shows only a fixed set of Claude surfaces, and excludes internal monitoring traffic, its call counts won't add up to the 30-day tool call total above. That's expected.
66Because the per-product table covers a shorter window, drops low-volume rows, shows only a fixed set of Claude surfaces, and excludes internal monitoring traffic, its call counts won't add up to the 30-day **Tool calls** total.
6767
6868A high error rate on a single product may reflect a client-side issue on Anthropic's end rather than a problem with your server.
6969
from line 73
7373
7474## Edit your listing
7575
76Open your submission's detail page to edit the listing. You can change directly:
76You edit a published listing from its submission detail page in the dashboard. You can change these fields directly:
7777
78* **Listing metadata**: tagline, description, categories, documentation and privacy policy links, support contact, and icon
78* **Listing metadata**: tagline, description, categories, tool and prompt names, documentation and privacy policy links, support contact, and icon
7979* **Company details**: company name and website
8080* **Display name**: editable, but changing the name of a published server affects existing users and requires re-review
8181
8282Save your edits as you go, then submit them for review. Submitted changes show as pending until a reviewer approves them, and you can discard pending changes before they're approved.
8383
84The URL slug is locked: it's permanent after publication, since it determines your listing URL.
84The URL slug is locked. It's permanent after publication because it determines your listing URL.
8585
87
88## Next steps
89
90* [After publishing](/docs/connectors/building/after-publishing): release updates to your server, and delist
91* [Connector verification](/docs/connectors/verification#list-your-own-connector): see how a Community listing becomes Verified
92* [Troubleshoot your connector](/docs/connectors/building/troubleshooting): diagnose the errors behind a degraded health badge or high error rate
8793
No line in this hunk matches that.