LaunchBuddy: Builder Tools and Launch Audits MCP server
io.github.msanchezgrice/launchbuddymsanchezgricestreamable-httpv0.4.0Scanned
Find builder resources, plan your next test, and audit public-site launch readiness.
16 tools: 2 can delete or cancel things, 10 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 6
- Can send data out · 3
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the LaunchBuddy: Builder Tools and Launch Audits MCP server can do
The LaunchBuddy: Builder Tools and Launch Audits MCP server is published by the GitHub account msanchezgrice. It has 16 tools. It can delete or cancel things (2 tools: reassess_launch and update_launch_todo) and create or change data (10 tools: verify_launch_audit, audit_my_launch, assess_launch, claim_assessment and 6 more). 4 tools only read.
6 tools bring in text other people can write (verify_launch_audit, audit_my_launch, get_launch_resource and 3 more); 3 tools can send data out of your system (verify_launch_audit, audit_my_launch and assess_launch).
The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 0.4.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
16 tools
Deletes or cancels 2Claude Code: deny
reassess_launchReassess a connected project after changes and compare its score without creating a second project.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Reassess a connected project after changes and compare its score without creating a second project. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Reassess Launch
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
update_launch_todoUpdate one owned launch task without starting provider work.No findings
Why it is in this group
- The name "update_launch_todo" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update one owned launch task without starting provider work. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Update Launch Todo
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
Changes things 10Claude Code: ask
assess_launchAssess a public launch URL and return the scored launch gaps plus a durable report URL.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Assess a public launch URL and return the scored launch gaps plus a durable report URL. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Assess Launch
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
audit_my_launchAudit a public URL across selected launch, technical, and agent-readiness checks.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Audit a public URL across selected launch, technical, and agent-readiness checks. Return separate scores, evidence, fix packs, and matching resources. No account actions, provider generation, or publishing. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Audit My Launch
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
claim_assessmentSave an anonymous assessment to the connected account without scanning again or starting a trial.No findings
Why it is in this group
- The description's first verb is "save": a word for a change.
Description, as the server wrote it Save an anonymous assessment to the connected account without scanning again or starting a trial. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Claim Assessment
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_growth_planCreate or read the free cached plan of ranked launch work for a connected project.No findings
Why it is in this group
- The name "create_growth_plan" says "create": a word for a change.
Description, as the server wrote it Create or read the free cached plan of ranked launch work for a connected project. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Create Growth Plan
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_recommended_assetPrepare the highest-priority asset.No findings
Why it is in this group
- The name "create_recommended_asset" says "create": a word for a change.
Description, as the server wrote it Prepare the highest-priority asset. Never charges or publishes; returns a resumable paid/approval handoff when required. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Create Recommended Asset
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
get_accessExplain the current identity, trial, paid entitlement, and available capabilities.1 finding
Why it is in this group
- The name "get_access" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "get_access" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_access" says "get": a word for reading.
Description, as the server wrote it Explain the current identity, trial, paid entitlement, and available capabilities. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Get Access
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
get_action_intentRead the resumable payment, approval, render, and verification state after a web handoff.Reads text others write1 finding
Why it is in this group
- The name "get_action_intent" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe description's first sentence says "read" and "web": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "get_action_intent" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_action_intent" says "get": a word for reading.
Description, as the server wrote it Read the resumable payment, approval, render, and verification state after a web handoff. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Get Action Intent
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
get_launch_todosRead the connected project checklist and its completion progress.1 finding
Why it is in this group
- The name "get_launch_todos" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "get_launch_todos" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_launch_todos" says "get": a word for reading.
Description, as the server wrote it Read the connected project checklist and its completion progress. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Get Launch Todos
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
preview_recommended_assetPreview the highest-priority asset brief without starting provider spend.1 finding
Why it is in this group
- The name "preview_recommended_asset" says "preview": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "preview_recommended_asset" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "preview_recommended_asset" says "preview": a word for reading.
Description, as the server wrote it Preview the highest-priority asset brief without starting provider spend. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Preview Recommended Asset
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
verify_launch_auditRecheck the native findings from a saved audit after changes are live.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Recheck the native findings from a saved audit after changes are live. Preserve unavailable checks as unobservable. Requires original audit JSON for the same URL. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Verify Launch Audit
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 4Show 4 read-only tools
get_assessmentRead a saved public LaunchBuddy assessment by scan id.No findings
Why it is in this group
- The name "get_assessment" says "get": a word for reading.
Description, as the server wrote it Read a saved public LaunchBuddy assessment by scan id. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Get Assessment
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_launch_resourceRead one public launch resource by its stable ID, including canonical URL and channel availability where applicable.Reads text others writeNo findings
Why it is in this group
- The name "get_launch_resource" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "read" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Read one public launch resource by its stable ID, including canonical URL and channel availability where applicable. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Get Launch Resource
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_projectsList the connected account's LaunchBuddy projects.No findings
Why it is in this group
- The name "list_projects" says "list": a word for reading.
Description, as the server wrote it List the connected account's LaunchBuddy projects. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: List Projects
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_launch_resourcesFind relevant public LaunchBuddy guides, free tools, skills, and relevant launch channels for a specific gap.No findings
Why it is in this group
- The name "search_launch_resources" says "search": a word for reading.
Description, as the server wrote it Find relevant public LaunchBuddy guides, free tools, skills, and relevant launch channels for a specific gap. Channel presence never proves eligibility, supported submission, or publication. Documentation: https://launchbuddy.com/agents.
Annotations the server declares
- title: Search Launch Resources
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:22 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 12
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 12 tools that change things (2 destructive, 10 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://launchbuddy.com/api/mcp: tools/list returned 16 tools to an anonymous client, including reassess_launch (destructive), update_launch_todo (destructive), verify_launch_audit (write), audit_my_launch (write), assess_launch (write) and 7 more
Findings
Matches of fixed checks, with the text they matched.
- Warnget_launch_todos
The server marks "get_launch_todos" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_launch_todos" says "get": a word for reading.
The server marks "preview_recommended_asset" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "preview_recommended_asset" says "preview": a word for reading.
The server marks "get_action_intent" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_action_intent" says "get": a word for reading.
- Warnget_access
The server marks "get_access" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_access" says "get": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools16 changed.~16 changedView diff
- Changed:assess_launchChanges thingstitledescriptionannotations
- Changed:audit_my_launchChanges thingstitledescriptionannotations
- Changed:claim_assessmentChanges thingstitledescriptionannotations
- Changed:create_growth_planChanges thingstitledescriptionannotations
- Changed:create_recommended_assetChanges thingstitledescriptionannotations
- Changed:get_accessChanges thingstitledescriptionannotations
- Changed:get_action_intentChanges thingstitledescriptionannotations
- Changed:get_assessmentOnly readstitledescriptionannotations
- Changed:get_launch_resourceOnly readstitledescriptionannotations
- Changed:get_launch_todosChanges thingstitledescriptionannotations
- Changed:list_projectsOnly readstitledescriptionannotations
- Changed:preview_recommended_assetChanges thingstitledescriptionannotations
- Changed:reassess_launchDeletes or cancelstitledescriptionannotations
- Changed:search_launch_resourcesOnly readstitledescriptionannotations
- Changed:update_launch_todoDeletes or cancelstitledescriptionannotations
- Changed:verify_launch_auditChanges thingstitledescriptionannotations
Install
Pinned to version 0.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http launchbuddy https://launchbuddy.com/api/mcpclaude mcp add --transport http launchbuddy https://launchbuddy.com/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__launchbuddy__search_launch_resources",
"mcp__launchbuddy__get_launch_resource",
"mcp__launchbuddy__get_assessment",
"mcp__launchbuddy__list_projects"
],
"ask": [
"mcp__launchbuddy__verify_launch_audit",
"mcp__launchbuddy__audit_my_launch",
"mcp__launchbuddy__assess_launch",
"mcp__launchbuddy__claim_assessment",
"mcp__launchbuddy__create_growth_plan",
"mcp__launchbuddy__get_launch_todos",
"mcp__launchbuddy__preview_recommended_asset",
"mcp__launchbuddy__create_recommended_asset",
"mcp__launchbuddy__get_action_intent",
"mcp__launchbuddy__get_access"
],
"deny": [
"mcp__launchbuddy__reassess_launch",
"mcp__launchbuddy__update_launch_todo"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as launchbuddy. Review it before you use it.
Capability tags behind 6 rules
- mcp__launchbuddy__verify_launch_audit untrusted-input, outbound
- mcp__launchbuddy__audit_my_launch untrusted-input, outbound
- mcp__launchbuddy__get_launch_resource untrusted-input
- mcp__launchbuddy__assess_launch untrusted-input, outbound
- mcp__launchbuddy__reassess_launch untrusted-input
- mcp__launchbuddy__get_action_intent untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.msanchezgrice/launchbuddy/verify?hash=052418525dd93c8f6b848ef072969de4b0bb408ccd3e76f3caa521f555633afb" | jq -e '.changed == false'Pinned hash 052418525dd9, from Nov 19, 2026, 16:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.msanchezgrice/launchbuddy/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.msanchezgrice/launchbuddy)Source: MCP Registry. Synced Nov 5, 2026, 18:17 UTC.
LaunchBuddy: Builder Tools and Launch Audits MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the LaunchBuddy: Builder Tools and Launch Audits MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 12 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the LaunchBuddy: Builder Tools and Launch Audits MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: reassess_launch and update_launch_todo.
Can the LaunchBuddy: Builder Tools and Launch Audits MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the LaunchBuddy: Builder Tools and Launch Audits MCP server have?
- 16 tools: 2 destructive, 10 write, 4 read. reassess_launch, update_launch_todo, verify_launch_audit, audit_my_launch, assess_launch, claim_assessment, create_growth_plan, get_launch_todos and 8 more.
Does the LaunchBuddy: Builder Tools and Launch Audits MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the LaunchBuddy: Builder Tools and Launch Audits MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): verify_launch_audit, audit_my_launch and assess_launch.
Has the LaunchBuddy: Builder Tools and Launch Audits MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.