
Spikes
Spikes turns UI feedback into structured data your agent can act on immediately. It exposes nine MCP tools including get_spikes for filtered feedback lists, get_hotspots to surface problem areas, submit_spike for programmatic annotations, and resolve_spike to close the loop. Reviewers click elements on live pages and rate them, capturing exact selectors and context. Your agent pulls that feedback as JSON, makes changes, and marks items resolved. Supports both local JSONL storage and a hosted backend at spikes.sh. If you're building prototypes with AI assistance and need to route human feedback back to the agent without screenshots or vague descriptions, this closes that gap.
- GitHub stars
- 1
- tools
- 16
- auth
- Secret needed
- transport
- STDIO
- env vars
- 2
- last updated
- Apr 28, 2026
Tools
16 toolsPublic tool metadata for what this MCP can expose to an agent.
get_spikesList feedback with filters (page, rating, unresolved, url_prefix, since)
List feedback with filters (page, rating, unresolved, url_prefix, since)
No parameter schema in public metadata yet.
get_element_feedbackGet feedback for a specific CSS selector
Get feedback for a specific CSS selector
No parameter schema in public metadata yet.
get_hotspotsFind elements with the most feedback
Find elements with the most feedback
No parameter schema in public metadata yet.
submit_spikeCreate feedback programmatically
Create feedback programmatically
No parameter schema in public metadata yet.
resolve_spikeMark feedback as addressed
Mark feedback as addressed
No parameter schema in public metadata yet.
delete_spikeRemove a spike
Remove a spike
No parameter schema in public metadata yet.
create_shareUpload files, get a shareable URL
Upload files, get a shareable URL
No parameter schema in public metadata yet.
list_sharesSee your active shares
See your active shares
No parameter schema in public metadata yet.
get_usageCheck usage stats, limits, and spend
Check usage stats, limits, and spend
No parameter schema in public metadata yet.
reply_to_spikeAnswer a reviewer on the page, optionally with a status and version (hosted)
Answer a reviewer on the page, optionally with a status and version (hosted)
No parameter schema in public metadata yet.
set_spike_statusMark a spike open, addressed, or won't do (hosted)
Mark a spike open, addressed, or won't do (hosted)
No parameter schema in public metadata yet.
list_versionsDeclare review versions and see counts per version (hosted)
Declare review versions and see counts per version (hosted)
No parameter schema in public metadata yet.
add_versionDeclare review versions and see counts per version (hosted)
Declare review versions and see counts per version (hosted)
No parameter schema in public metadata yet.
list_questionsAsk reviewers questions and read answers (hosted)
Ask reviewers questions and read answers (hosted)
No parameter schema in public metadata yet.
ask_questionAsk reviewers questions and read answers (hosted)
Ask reviewers questions and read answers (hosted)
No parameter schema in public metadata yet.
get_question_answersAsk reviewers questions and read answers (hosted)
Ask reviewers questions and read answers (hosted)
No parameter schema in public metadata yet.
Sponsors
Configuration
SPIKES_TOKENsecretBearer token for the hosted Spikes API. Required only when using --remote mode against spikes.sh. Local mode reads .spikes/feedback.jsonl and needs no token.
SPIKES_API_URLOverride the Spikes API base URL. Defaults to https://spikes.sh/api. Useful for self-hosted Spikes workers.
Readme
/ Spikes
The feedback loop for AI-assisted building
AI can build a prototype in an hour.
Turning feedback into action is still the slow part.
Quick Start · CLI Reference · Widget Docs · Hosted Dashboard · Self-Hosting
What Is This?
Spikes is a feedback tool for AI-assisted development. It lets reviewers leave targeted feedback directly on web pages — no screenshots, no "that button over there", no lost context.
Click any element. Rate it. Comment. Spikes captures the exact CSS selector, bounding box, and page context. Your AI agent gets structured JSON it can act on immediately.
No accounts required. No build step. Works on file://, localhost, anywhere.
Quick Start
1. Install the CLI
Details
- Repository
- github.com/bierlingm/spikes
- Package
spikes-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active