Hear what agents think of your MCP server
Your server can return valid JSON and still make an agent guess through five calls. Emic gives that agent a direct research channel after the work is done.
- For
- Teams building MCP servers, toolkits, and agent integrations
- Question
- Collect qualitative feedback from AI agents using an MCP server
- Start with
- Pick the one search or create tool that generates the most support questions, and study only that.
- Updated
“The search worked, but I had to guess whether owner accepted a login or an organization name. One example would have removed two retries.”
Requested changeAdd an owner filter example to the tool description.
{
"tool": "submit_agent_feedback",
"arguments": {
"feedback_type": "docs_feedback",
"tool_or_endpoint": "search_repositories",
"summary": "The search worked, but I had to guess whether owner accepted a login or an organization name. One example would have removed two retries.",
"outcome": "success",
"satisfaction": 3,
"suggested_fix": "Add an owner filter example to the tool description."
}
}A synthetic example in the shape a real report takes. Emic never manufactures a report from observed behavior.
What this research can teach youThree things a success metric cannot tell you about this workflow.
Which descriptions force a guess
Agents can name ambiguous parameters, missing examples, and schema promises that do not match the returned object.
Where one job becomes many calls
A successful run can still expose missing compound tools, pagination, lookups, or safe recovery paths.
What agents tried to do next
Feature requests arrive with the attempted job and the workaround, not as an abstract wish list.
Where the research channel actually has to liveA tool the model never sees is a tool that never gets used.
The filing line has to live where the client actually reads
A healthy MCP connection does not prove the agent saw the research affordance. One persisted report from the normal client does.
From one question to a product decision5 moves, in order. Each one produces something you can point at.
Choose one real tool flow
Start with a workflow that already receives agent traffic, such as search, create, or update.
A bounded research surfaceExpose the direct feedback tools
Add submit_agent_feedback and get_unblocked beside the MCP tools the agent already sees.
An explicit filing pathSet the filing norm
Tell the agent when feedback is useful: after confusing, missing, broken, unusually slow, or excellent experiences.
A visible invitation to reportRead reports by lane and tool
Review the agent wording, outcome, satisfaction, affected tool, and requested change.
Stated evidence with contextChange one thing and listen again
Ship the description, schema, documentation, or tool change and compare the next direct reports.
A research loop, not a trace dashboardWhat the direct channel records, and what it never touchesThe default install is additive. It adds two tools and changes nothing else.
The research submission
- The report the agent chooses to file
- The named tool or endpoint
- Outcome and satisfaction supplied by the agent
- Optional requested change and survey answers
Everything else
- Existing MCP tool arguments and results
- Prompts, messages, and private transcripts
- The hot path of the original tool call
- Unrelated sessions and workflows
One paste, then verify a real reportA healthy endpoint is not an active study. The inbox record is the proof.
Install Emic into this project: add submit_agent_feedback and get_unblocked as direct tools. Never wrap or record existing tool calls, arguments, results, errors, transcripts, or messages. Additive only, plain HTTP, zero dependencies. Full instructions: https://emic.sh/llms-full.txt
The agent writes the handler, registers the two tools beside your existing ones, and verifies its own install by checking the response. Nothing is placed in front of the tools you already ship.
- Adds
submit_agent_feedbackandget_unblocked, as direct tools- Never touches
- Existing tool calls, arguments, results, errors, messages, and transcripts
- Agents read
emic.sh/llms-full.txt- Start with
- Pick the one search or create tool that generates the most support questions, and study only that.
The method, without collapsing the evidence
Protocol compliance is not agent experience
A trace can prove that the tool returned a result. It cannot tell you that the agent misunderstood the description, searched the wrong namespace first, or wished the server exposed a safer primitive.
Direct feedback preserves the user account of the experience. That makes it useful for product, documentation, and API design decisions that success rates alone cannot settle.
Pick the flow with the most guessing
Do not instrument the entire server on day one. Choose a flow where support questions, retries, or workaround code already suggest uncertainty.
- Search tools with several similar filters
- Create tools with required foreign identifiers
- List tools without pagination guidance
- Update tools with partial and destructive modes
Questions teams ask before starting
Does Emic proxy my MCP tool calls?
No. The default install adds direct research tools. It does not wrap, proxy, or record the tools your server already exposes.
Will every agent file feedback?
No. Filing depends on whether the tool and the norm are actually visible in the agent context. The first goal is to prove one real report in one bounded workflow.
Can I ask a follow-up question?
Yes. An exit survey can ride in the response and the agent can answer directly. Keep the question short and tied to the work it just completed.
Follow the problem, not a keyword trailAdjacent routes are chosen by the decision they inform.
Agent docs feedback
An agent can complete the task and still tell you that the docs made it expensive. Capture the missing example or ambiguous contract while the workaround is fresh.
Read next Use cases · Workflow frictionSuccessful but painful work
Failure is visible. Friction often disappears into a successful final result. Direct reports reveal the retries, detours, and missing primitives inside that success.
Read next Guides · Implementation guideCollect feedback from agents
Add a direct tool, make the filing norm visible, verify one real report, and keep the research channel separate from the product path it studies.
Read nextPut one MCP workflow in front of its users
Install the direct tools, verify the agent can see them, and collect the first real report before expanding the study.
The assisted 14-day pilot costs nothing. Start with one isolated workflow, and remove Emic by deleting the two tools it added.
- One paste to install
- 0ms on your hot path
- 14-day assisted pilot
- Two added tools to remove