First-party observed usage
This snapshot groups exact tool names shaped like mcp__server__tool into server-level totals. It ranks observed invocation activity—not installs, GitHub stars, registry popularity, satisfaction, or industry-wide market share.
What the data says
Claude In Chrome leads this eligible snapshot by calls with 41,128 observed invocations across 10 exact tool names, with an observed error-call rate of 4.6%.
Eligible server calls
86,659
Across servers meeting the 5-call floor.
Attributed turn tokens
22.08B
Model-turn tokens attributed to MCP calls, not MCP execution cost.
Observed error calls
4,514
5.2% of eligible calls.
Eligible servers
20
0 below the public ranking floor.
Claude In Chrome
10 exact tools · 9.21B attributed turn tokens
Claude Browser
7 exact tools · 4.38B attributed turn tokens
Claude Preview
4 exact tools · 2.09B attributed turn tokens
Chrome Devtools
3 exact tools · 712.2M attributed turn tokens
Claude Ai Slack
1 exact tools · 269.4M attributed turn tokens
Plugin Playwright Playwright
4 exact tools · 817.9M attributed turn tokens
Claude Code IOS Simulator
1 exact tools · 1.52B attributed turn tokens
Claude Ai PostHog
1 exact tools · 272.0M attributed turn tokens
Linear Server
2 exact tools · 507.3M attributed turn tokens
Ccd Session
1 exact tools · 232.3M attributed turn tokens
Server totals are sums of the additive fields below. Developer counts are intentionally omitted: adding distinct-developer counts from several tools would count the same person more than once.
Call volume shows how often an MCP server's observed tools were invoked. Attributed tokens reflect the surrounding model work and can be high for context-heavy tasks even when the server itself returns a small response. Neither measure establishes adoption outside this cohort.
Error rate is descriptive, not causal. A failed call can reflect authentication, invalid arguments, network conditions, permissions, upstream services, or the server. Compare it only with the sample size and exact tool mix visible on this page.
Snapshot coverage. The page reads toolCalls from the public insights response. These values come from each listed participant's latest submitted transcript snapshot; they are overwritten on a new submission and are not a trailing-30-day time series. The displayed generation date identifies the API snapshot rendered here.
Server grouping. Only exact names matching mcp__server__tool are included. The text between the first and second double-underscore separators is the server key. Calls, attributed tokens, and errors are additive across exact tool rows; distinct-developer counts are not aggregated because the API does not expose a server-level union.
Sample floor. A server must have at least 5 observed calls to enter the ranking. This reduces one-off noise but does not make the sample representative or a statistical benchmark.
Result ceiling. The API returns at most 100 skill/tool-call rows after ranking built-in and MCP tools together. Lower-volume MCP tools may therefore be absent, so the table is a ranked view of returned observations—not a complete registry of every installed or invoked MCP server.
Cohort and attribution limits. Public participation is opt-in and not weighted to represent all AI coding users. Token values belong to the model turn containing each call and are split across calls in multi-tool turns. Do not interpret them as the MCP server's direct execution cost, latency, or resource use.
Aggregated model, agent, trend, skill, and tool-call totals from participating developers.
Explains what the CLI aggregates, what it does not collect, and the limits of the public cohort.
| 712.2M |
| 74 |
| 2.1% |
| Claude Ai Slack | 1 | 3,209 | 269.4M | 23 | 0.7% |
| Plugin Playwright Playwright | 4 | 2,599 | 817.9M | 114 | 4.4% |
| Claude Code IOS Simulator | 1 | 2,565 | 1.52B | 43 | 1.7% |
| Claude Ai PostHog | 1 | 1,758 | 272.0M | 79 | 4.5% |
| Linear Server | 2 | 1,562 | 507.3M | 27 | 1.7% |
| Ccd Session | 1 | 1,513 | 232.3M | 2 | 0.1% |
| Kroda | 1 | 1,414 | 151.0M | 17 | 1.2% |
| Sequential Thinking | 1 | 1,098 | 345.2M | 6 | 0.5% |
| Supabase | 1 | 943 | 188.8M | 112 | 12% |
| Claude In Chrome | 2 | 839 | 386.8M | 73 | 8.7% |
| Claude Ai Gmail | 1 | 780 | 197.0M | 5 | 0.6% |
| Linear | 1 | 601 | 194.2M | 16 | 2.7% |
| F8c1d5be Ee16 4e8b Afa2 3b6c6d1d4c69 | 1 | 599 | 166.3M | 44 | 7.3% |
| Playwright | 1 | 563 | 126.0M | 83 | 15% |
| Claude Ai Linear | 1 | 402 | 176.7M | 10 | 2.5% |
| Grafana | 1 | 342 | 140.3M | 21 | 6.1% |
| Claude In Chrome |
| 7,071 |
| 1.94B |
| 408 |
| 5.8% |
mcp__Claude_Browser__computer | Claude Browser | 5,131 | 1.50B | 507 | 9.9% |
mcp__Claude_Preview__preview_eval | Claude Preview | 4,620 | 1.41B | 268 | 5.8% |
mcp__Claude_Browser__javascript_tool | Claude Browser | 4,453 | 1.40B | 286 | 6.4% |
mcp__claude-in-chrome__navigate | Claude In Chrome | 4,134 | 902.3M | 203 | 4.9% |
mcp__claude_ai_Slack__slack_read_channel | Claude Ai Slack | 3,209 | 269.4M | 23 | 0.7% |
mcp__Claude_Code_iOS_Simulator__control | Claude Code IOS Simulator | 2,565 | 1.52B | 43 | 1.7% |
mcp__chrome-devtools__evaluate_script | Chrome Devtools | 2,160 | 386.5M | 49 | 2.3% |
mcp__Claude_Browser__navigate | Claude Browser | 1,926 | 636.9M | 277 | 14% |
mcp__claude-in-chrome__tabs_context_mcp | Claude In Chrome | 1,907 | 405.3M | 46 | 2.4% |
mcp__claude_ai_PostHog__exec | Claude Ai PostHog | 1,758 | 272.0M | 79 | 4.5% |
mcp__ccd_session__mark_chapter | Ccd Session | 1,513 | 232.3M | 2 | 0.1% |
mcp__kroda__http_send | Kroda | 1,414 | 151.0M | 17 | 1.2% |
mcp__Claude_Preview__preview_screenshot | Claude Preview | 1,254 | 370.2M | 176 | 14% |
mcp__sequential-thinking__sequentialthinking | Sequential Thinking | 1,098 | 345.2M | 6 | 0.5% |
mcp__claude-in-chrome__find | Claude In Chrome | 1,078 | 270.7M | 125 | 12% |
mcp__Claude_Browser__preview_start | Claude Browser | 996 | 324.1M | 111 | 11% |
mcp__linear-server__save_issue | Linear Server | 987 | 325.5M | 23 | 2.3% |
mcp__supabase__execute_sql | Supabase | 943 | 188.8M | 112 | 12% |
mcp__chrome-devtools__navigate_page | Chrome Devtools | 917 | 206.1M | 16 | 1.7% |
mcp__plugin_playwright_playwright__browser_evaluate | Plugin Playwright Playwright | 866 | 266.3M | 28 | 3.2% |
mcp__claude-in-chrome__get_page_text | Claude In Chrome | 815 | 131.9M | 43 | 5.3% |
mcp__claude_ai_Gmail__create_draft | Claude Ai Gmail | 780 | 197.0M | 5 | 0.6% |
mcp__Claude_Browser__resize_window | Claude Browser | 772 | 225.3M | 41 | 5.3% |
mcp__plugin_playwright_playwright__browser_navigate | Plugin Playwright Playwright | 753 | 226.1M | 32 | 4.2% |
mcp__plugin_playwright_playwright__browser_take_screenshot | Plugin Playwright Playwright | 625 | 196.9M | 12 | 1.9% |
mcp__linear__save_issue | Linear | 601 | 194.2M | 16 | 2.7% |
mcp__f8c1d5be-ee16-4e8b-afa2-3b6c6d1d4c69__execute_sql | F8c1d5be Ee16 4e8b Afa2 3b6c6d1d4c69 | 599 | 166.3M | 44 | 7.3% |
mcp__Claude_Preview__preview_start | Claude Preview | 589 | 135.0M | 204 | 35% |
mcp__linear-server__save_comment | Linear Server | 575 | 181.8M | 4 | 0.7% |
mcp__claude-in-chrome__read_page | Claude In Chrome | 568 | 115.3M | 24 | 4.2% |
mcp__playwright__browser_navigate | Playwright | 563 | 126.0M | 83 | 15% |
mcp__Claude_Preview__preview_console_logs | Claude Preview | 523 | 175.0M | 2 | 0.4% |
mcp__Claude_in_Chrome__computer | Claude In Chrome | 512 | 275.7M | 41 | 8.0% |
mcp__Claude_Browser__read_page | Claude Browser | 509 | 144.8M | 1 | 0.2% |
mcp__claude-in-chrome__tabs_close_mcp | Claude In Chrome | 468 | 122.7M | 11 | 2.4% |
mcp__Claude_Browser__read_console_messages | Claude Browser | 461 | 145.2M | 4 | 0.9% |
mcp__chrome-devtools__take_screenshot | Chrome Devtools | 433 | 119.6M | 9 | 2.1% |
mcp__claude_ai_Linear__save_issue | Claude Ai Linear | 402 | 176.7M | 10 | 2.5% |
mcp__plugin_playwright_playwright__browser_click | Plugin Playwright Playwright | 355 | 128.6M | 42 | 12% |
mcp__grafana__query_prometheus | Grafana | 342 | 140.3M | 21 | 6.1% |
mcp__claude-in-chrome__form_input | Claude In Chrome | 340 | 113.3M | 24 | 7.1% |
mcp__Claude_in_Chrome__browser_batch | Claude In Chrome | 327 | 111.1M | 32 | 9.8% |