Chapa MCP server
online · 100% uptimeio.github.juan294/chapa·v2.29.1·1 starsRead, compare, and verify public developer impact profiles and Chapa badges.
1 stars
Reviews
Write oneNobody has reviewed Chapa yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Chapa tools (9)
write = sends, deletes, buys or postscompare_profilesFreeCompare two public Chapa impact profiles by the headline each badge draws.
explain_dimensionFreeExplain one impact dimension from the selected policy receipt, including sealed v7.4 or v7.5 contributions and outcome availability, automatic Quality and optional reviewed bonus.
explain_verificationFreeExplain Chapa badge verification guarantees and limits.
find_profileFreeResolve a GitHub handle to its Chapa profile and badge URLs.
get_embed_snippetFreeReturn ready-to-paste Markdown and HTML for a live Chapa badge.
get_impact_historyFreeReturn policy-labelled daily receipt winners and trends for a GitHub handle, including the desired policy and upgrade state.
get_impact_profileFreeReturn the selected policy receipt, including v7.4 or v7.5 recorded activity and product outcomes for a GitHub handle, including its policy, identity, exact/display points and Quality breakdown. When no receipt is drawable, return scoringStatus and the initial Emerging archetype for registered users.
get_site_capabilitiesFreeDescribe Chapa and list its agent-facing tools and entry points.
verify_badgeFreeLook up the public verification result for a Chapa badge hash.
Public scan report
scanner v0.1.10 · 2026-10-29 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 1046ms20/20
- Tool poisoning9 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityno repository or website to verify2/10
How Chapa compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 67/100
- higher than 25% of 48,243 servers
- Tools
- 9
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 259 ms
- faster than 57% of 30,027 servers
- GitHub stars
- 1
- more than 65% of 28,706 servers
What its tools let an agent do: 9 read
Install Chapa in Claude Code, Cursor or VS Code
claude mcp add --transport http chapa https://chapa.thecreativetoken.com/api/mcp
What the publisher says
From the Chapa repository's README, as published. We do not edit it. Read it on GitHub
Chapa — Developer Impact Badge
Generate a live, embeddable, animated SVG badge that showcases your developer impact from GitHub, Bitbucket, Codeberg, and GitLab activity — with multi-dimensional scoring, verification, and one-click sharing.
WebMCP
Chapa adds a WebMCP layer to four surfaces: the landing page, the Creator Studio, and the public profile and verification pages. The landing page is the front door, where getsitecapabilities returns a map of every route and the tools it carries, so an agent can find the right page instead of guessing at one. Studio tools reuse the existing command registry, so agent actions update the same preview and terminal that the user sees. Saving is always human-gated; in judge demo mode (/studio?demo=1), confirmed saves stay local and never write production data. Landing, public profile, and verification tools are read-only.
Registration uses the current document.modelContext.registerTool(tool, { signal }) contract, an AbortController for cleanup, feature detection for unsupported clients, and a remote feature-flag kill switch.
See the WebMCP tool catalog and judge guide and the under-three-minute demo script and submission checklist.
The write-up WebMCP, Explained. And What Happened When I Shipped It (published on X, LinkedIn and Medium) covers the design framework, the tested tool-map contract, and the rules that came out of shipping it. The production demo transcript (2026-09-01, Chrome 151 with the WebMCP flag) records an agent driving all four surfaces end to end, and is linked from the landing page as the agent-tested proof. A companion note, The WebMCP directories made me use a mouse, records what the directory submissions taught.
The catalog's Design methodology documents each user goal, initial state, role-play, and recovery path.
Runtime status: a preview-only chapa_hello spike passed native registration, discovery, and execution in flagged Chrome 151 on 2026-08-27, and the production preflight on 2026-09-01 found all 19 registrations across 18 distinct names on four surfaces (see the transcript above). Chapa is listed on webmcp.com, in the official MCP Registry as io.github.juan294/chapa, and as an ownership-verified Glama connector. The ChatGPT in-app client was unavailable for the spike, so this README does not claim ChatGPT runtime validation.
Prior work and submission-period work
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-10-29downgradeA → Cscore 67
Chapa: common questions
- Is Chapa MCP server safe?
- With care: it is graded C, so read the findings first (67/100). Read the Chapa safety report
- How do I install Chapa?
- It runs remotely at chapa.thecreativetoken.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Chapa need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Chapa maintained?
- The last commit was 53 days ago (2026-09-14). The latest release is v2.29.1.
- Is Chapa up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Chapa compare with other MCP servers?
- safety score 67/100 (higher than 25% of 48,243 servers); tools 9 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.