Your coding agent should know what your customers said

Modem released its MCP server and public API for all users, enabling coding agents to search synthesized customer feedback from Slack, Intercom, Linear, and other sources in a single call. The company reported that using Modem's MCP server consumed 28,255 tokens per query, compared to 66,404 tokens (2.4×) for GitHub CLI, 70,966 tokens (2.5×) for Linear MCP, 72,180 tokens (2.6×) for Slack MCP, and 129,558 tokens (4.6×) for querying all three sources separately. The tool returns deduplicated findings with reporter counts, and includes read tools, write tools, and a subagent for cross-source reasoning.

All posts /blog Your coding agent should know what your customers said Modem's MCP server and public API are now available for all Modem users. Any MCP client can connect at https://mcp.modem.dev/mcp. As we build, we've found it useful to pull relevant customer feedback into the work: who hit this bug, what they expected, what they asked for. It keeps us building the right thing. Your agent can already reach those sources one at a time: Slack has an MCP server, and so do Intercom, Linear and others. But what comes back is raw material: threads, tickets and duplicate reports, one tool at a time. Modem synthesizes the feedback from all of those connections into topics, deduplicated findings with the evidence and reporter counts attached. Our MCP server hands your agent that synthesis. Now the agent can just ask. What your agent gets Connect Modem over MCP and your coding agent gains three things: Read tools : search modem takes a plain-English question and searches your synthesized topics, returning findings with their evidence and reporter counts attached. Write tools : merge topics for duplicates, update topic to reprioritize, create companies to create or link companies, and more, all without leaving the session. Subagent : invoke modem agent runs the full Modem agent, for questions that need Slack, Gong, Intercom and topics reasoned over together. Building with user feedback Neil Chudleigh https://x.com/neilsuperduper builds superwhisper https://superwhisper.com , an AI-powered dictation app for macOS. He was mid-PR on a paste-detection bug: the recording window hung after dictating into Electron and browser apps, but worked in Apple Notes. From inside the coding session, he asked Modem what users had said. The reply: modem - search modem "recording window hangs after paste in electron" 3 related topics returned The results are grouped by relevance to the fix they had open. A dashboard cannot do that; it does not know what you are building. That top result is one of Modem's topics: reports from Slack and Discord, deduplicated into a single finding with a reporter count. Neil never had to read the 400 messages behind it. Recording window hangs after paste in Electron Fine in native apps. Reproduces in Electron and browser text fields. Sources: Slack · Discord Neil's verdict at the end of the session: pretty useful from mcp today We'll take it. How we wrote this post We found that story with the MCP server. To prep for writing this post, we asked the Modem MCP: That one question turned up customers who had asked for an API months before it existed. It also resurfaced Neil's story above, highlighting both his experience and his quote as evidence. Along the way we found a gap in our own product and filed a Linear issue for it from the same session, using the write tools. Token efficient Using Modem to search customer feedback is fast and token efficient. You can of course query each source directly — Slack, Linear, GitHub, Intercom — but those sources hand back raw threads and tickets, and the agent pays for every token it reads while piecing them together. We measured it: the same question in a fresh Claude Code session, restricted to one source at a time. Modem typically answered from a single search modem call. The other sessions searched, pulled threads and issues, and reconciled what came back. | Source | Tool calls | Tokens / questionsame question, fresh session | vs Modem | |---|---|---|---| | Modem · MCP | 1 | 28,255 | baseline | | GitHub · gh CLI | 32 | 66,404 | 2.4× | | Linear · MCP | 10 | 70,966 | 2.5× | | Slack · MCP | 10 | 72,180 | 2.6× | | All three · one session | 14 | 129,558 | 4.6× | Any single source used at least 2.4× the tokens, for a partial answer; each one only knows its own silo. Matching Modem's coverage meant querying all three in one session, at 4.6× the tokens. The synthesis had already happened before the session started, so the agent read findings instead of threads. Get started In Claude Code: Then run /mcp to authorize. Auth is OAuth in the browser; there is no API key to provision. Cursor, VS Code, Copilot, Codex and opencode connect to the same endpoint over Streamable HTTP, and the docs https://modem.dev/docs/api/modem-mcp-server have the per-client config. Then ask about whatever you are working on, the way you would type it mid-PR: If you want to push context into Modem from your own systems, there is also a public API at api.modem.dev/v1 . That one deserves its own post, coming soon; the API reference https://modem.dev/docs/api has the details today. Connect it and ask about the thing you are building today.