MergeSafe MCP server
ai.mergesafe/mergesafemergesafe.aistreamable-httpv1.0.1Scanned
The GitHub gatekeeper for builders: read review findings, fix them, ask for a re-review.
16 tools: 2 can delete or cancel things, 1 do something that can't be undone, 8 change things and 5 only read.
- Reads private data · 5
- Reads text others write · 3
- Can send data out · 1
- No findings
Sign-in required, OAuth metadata published. Remote posture
With Anlyon
2 tools here can delete or cancel things and 1 does something that can't be undone. 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 MergeSafe MCP server can do
The MergeSafe MCP server is published by mergesafe.ai, a domain the MCP Registry verified. It has 16 tools. It can delete or cancel things (2 tools: answer_finding and end_session), do things that cannot be undone, such as sending, paying or publishing (review_local) and create or change data (8 tools: request_review, request_review_with_context, start_session, review_branch and 4 more). 5 tools only read.
5 tools read private data (get_findings, get_settings, list_repositories and 2 more); 3 tools bring in text other people can write (get_findings, list_repositories and local_context_status); 1 tool can send data out of your system (review_local). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint asks for sign-in and publishes OAuth metadata.
Last scanned Nov 20, 2026, version 1.0.1.
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
answer_findingAnswer a finding once per review (free): 'won't fix here' or why it is intended.No 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).
Description, as the server wrote it Answer a finding once per review (free): 'won't fix here' or why it is intended. MergeSafe judges the reply and withdraws the finding, keeps it at P3, or notes it; get_session_findings shows the verdict. For a fix, just review_local again: the next review re-checks the file.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- title: Answer a finding
end_sessionClose the session; the uploaded code is deleted.No findings
Why it is in this group
- The description's first verb is "close": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Close the session; the uploaded code is deleted. Findings are kept.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- title: End the session
- idempotentHint: true
Can't be undone 1Claude Code: ask
review_localSend the local diff for review and get its quote.Can send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send the local diff for review and get its quote. Nothing runs yet: the answer says 'This review will cost you up to $X (Strong)' with the other levels' prices. Always show the user the price and ask them to confirm before you call confirm_review; never confirm on your own. Send each changed file with its patch and full text (none for a removed file). Also send context_files: the files that call, or are called by, the changed code (its callers and the modules it imports), because the review sees only what you send and cannot check effects in files it was not given. (at most 250000 bytes in all). Never send secrets. In a follow-up, only files changed since the last review are counted.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- title: Quote a local review
Changes things 8Claude Code: ask
approve_moreRaise the session's cost limit by amount_usd.No findings
Why it is in this group
- The name "approve_more" says "approve": a word for a change.
Description, as the server wrote it Raise the session's cost limit by amount_usd. Only after the user explicitly agreed to that amount; never on your own.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- title: Raise the session limit
confirm_reviewRun a quoted review at the level the user chose, ONLY after the user confirmed its price.No findings
Why it is in this group
- The description's first verb is "run": a word for a change.
Description, as the server wrote it Run a quoted review at the level the user chose, ONLY after the user confirmed its price. The price is held; what is charged afterwards is never more. If the session's limit would be passed, nothing runs: ask the user, and use approve_more only if they agree. Then poll get_session_findings.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- title: Run a confirmed review
prepare_uploadGet a short-lived upload token for this open session (10 minutes, one upload).No findings
Why it is in this group
- The name "prepare_upload" says "upload": a word for a change.
Description, as the server wrote it Get a short-lived upload token for this open session (10 minutes, one upload). The local process POSTs the review's files to upload_path with it, so the file contents never pass through you. Then call review_local with the upload_id it returns. Spends nothing.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- title: Prepare an upload
request_reviewAsk MergeSafe to review the current head of a pull request; MergeSafe posts the review on the pull request.No findings
Why it is in this group
- The name "request_review" says "request": a word for a change.
Description, as the server wrote it Ask MergeSafe to review the current head of a pull request; MergeSafe posts the review on the pull request. A head that was already reviewed is refused, not charged twice. Call it after pushing fixes.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- title: Request a review
- idempotentHint: true
request_review_with_contextLike request_review, but also sends excerpts of the tests of the files the pull request changes, read from your local checkout, so the review sees them.No findings
Why it is in this group
- The name "request_review_with_context" says "request": a word for a change.
Description, as the server wrote it Like request_review, but also sends excerpts of the tests of the files the pull request changes, read from your local checkout, so the review sees them. Only when local_context_status says enabled. Push first: head_sha is the commit you read at, and if the pull request's head is another commit nothing is queued (head_moved). For each changed source file, up to 3 test files named after it (test_foo.py, foo_test.go, foo.test.ts, foo.spec.js, FooTest.java, or foo.* in a tests directory); each item is {path, start_line: 1, end_line, sha: head_sha, text}: the file's first lines exactly as committed, at most 200 lines an item, 2000 lines and 150000 bytes in all. Never send secrets or files that are not tests; MergeSafe checks every excerpt against the commit.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- title: Request a review with local tests
- idempotentHint: true
review_branchReview a branch already pushed to GitHub, with no upload: MergeSafe reads the branch's changes from GitHub itself.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Review a branch already pushed to GitHub, with no upload: MergeSafe reads the branch's changes from GitHub itself. Returns review_id with status 'fetching' (queued). Poll get_session_findings until this review is 'quoted', then show the user its price as for review_local and ask them to confirm before confirm_review. A branch MergeSafe cannot read is refused with a note, and nothing is charged for it.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- title: Review a pushed branch
session_costThe session's total so far, its limit and what is left.No 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 read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The session's total so far, its limit and what is left.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- title: Session cost
start_sessionStart a MergeSafe review session for local changes, before or without a pull request; nothing is posted to GitHub.No findings
Why it is in this group
- The name "start_session" says "start": a word for a change.
Description, as the server wrote it Start a MergeSafe review session for local changes, before or without a pull request; nothing is posted to GitHub. FIRST ask the user for a cost limit for the session in US dollars and pass it as limit_usd: reviews stop when it is reached until the user approves more. Returns the session_id and how reviews are priced (level rate x review size).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- title: Start a local review session
Only reads 5Show 5 read-only tools
get_findingsList MergeSafe's findings on the latest review of a pull request.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_findings" says "get": a word for reading.
What it can reach
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
- untrusted-inputThe description's first sentence says "list" and "review": it reads comments, which other people can write.
Description, as the server wrote it List MergeSafe's findings on the latest review of a pull request. Each has severity (P0 most severe .. P3), title, problem, file, line, status, blocking and comment_url, the inline comment on GitHub that holds the full explanation and a prompt for fixing it. Loop: for each blocking finding, check the claim against the file as it stands now; if it holds, fix it and add a regression test; run the tests; commit and push; then call request_review. A finding of type question (needs_decision) asks whether a behavior is intended, with its severity_if_unintended; it does not block. It needs a decision, not just a fix, and it is likely a human one. Not intended: fix it (the fix answers it). Intended: say so on its thread; evidence helps (the PR's ticket, the PR description, a test, a doc or a file:line). Unsure: leave it open, or ask whoever owns the change.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- title: Get pull request findings
get_session_findingsThe session's findings (severity P0 most severe ..Reads private dataNo findings
Why it is in this group
- The name "get_session_findings" says "get": a word for reading.
What it can reach
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
Description, as the server wrote it The session's findings (severity P0 most severe .. P3, file, lines, problem, suggestion, status: open, withdrawn or kept_at_p3, and any answer's verdict; a finding whose answer could not be judged is open again and may be answered) and the state of its latest review: running, done with the price charged, or failed (never charged). Fix what holds, then review_local again; or answer a finding with answer_finding.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- title: Get session findings
get_settingsRead how this organization's MergeSafe is set up: for each setting its effective value, where the value comes from (repo_override, org, mixed with field_sources, mergesafe_default,…Reads private dataNo findings
Why it is in this group
- The name "get_settings" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "repo": it reads repositories.
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
Description, as the server wrote it Read how this organization's MergeSafe is set up: for each setting its effective value, where the value comes from (repo_override, org, mixed with field_sources, mergesafe_default, or unchecked when it could not be read) and the values it may take, plus the settings version. Give the org (its GitHub login); add repo for that repository's effective settings. Read-only. A Member sees no billing fields.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- title: Read settings
list_repositoriesList the repositories MergeSafe reviews for an organization, each with its effective level, plus the org's trigger mode and the GitHub link where the repository selection is change…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_repositories" says "list": a word for reading.
What it can reach
- private-dataThe name "list_repositories" says "list" and "repository": it reads repositories.
- private-dataThe description's first sentence says "list" and "repository": it reads repositories.
- untrusted-inputThe description's first sentence says "list" and "review": it reads comments, which other people can write.
Description, as the server wrote it List the repositories MergeSafe reviews for an organization, each with its effective level, plus the org's trigger mode and the GitHub link where the repository selection is changed (GitHub decides which repos are reviewed). Read-only. A Member sees only the repos their GitHub account can see.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- title: List reviewed repositories
local_context_statusWhether the repository's organization accepts local context (request_review_with_context).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "local_context_status" says "status": a word for reading.
What it can reach
- private-dataThe description's first sentence says "repository": it reads repositories.
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it Whether the repository's organization accepts local context (request_review_with_context). Ask before reading anything to send: when it is off, send nothing and use request_review.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- title: Check local context
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.
15 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data5
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__mergesafe__review_local"
]
}
}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, 18:18 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 401
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- yes
- resource_metadata in WWW-Authenticate
- https://mcp.mergesafe.ai/.well-known/oauth-protected-resource
- RFC 9728 protected resource metadata
- https://mcp.mergesafe.ai/.well-known/oauth-protected-resource
- Authorization servers
- https://app.mergesafe.ai
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http mergesafe https://mcp.mergesafe.aiclaude mcp add --transport http mergesafe https://mcp.mergesafe.aiRun 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__mergesafe__get_findings",
"mcp__mergesafe__get_settings",
"mcp__mergesafe__list_repositories",
"mcp__mergesafe__local_context_status",
"mcp__mergesafe__get_session_findings"
],
"ask": [
"mcp__mergesafe__request_review",
"mcp__mergesafe__request_review_with_context",
"mcp__mergesafe__start_session",
"mcp__mergesafe__review_local",
"mcp__mergesafe__review_branch",
"mcp__mergesafe__confirm_review",
"mcp__mergesafe__approve_more",
"mcp__mergesafe__session_cost",
"mcp__mergesafe__prepare_upload"
],
"deny": [
"mcp__mergesafe__answer_finding",
"mcp__mergesafe__end_session"
]
}
}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 mergesafe. Review it before you use it.
Capability tags behind 6 rules
- mcp__mergesafe__get_findings private-data, untrusted-input
- mcp__mergesafe__get_settings private-data
- mcp__mergesafe__list_repositories private-data, untrusted-input
- mcp__mergesafe__local_context_status private-data, untrusted-input
- mcp__mergesafe__review_local outbound
- mcp__mergesafe__get_session_findings private-data
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/ai.mergesafe/mergesafe/verify?hash=66d11101b9cce3235b64965f896fbe9d6ff622f2a4348ec1f25ab81c35c04e59" | jq -e '.changed == false'Pinned hash 66d11101b9cc, from Nov 20, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.mergesafe/mergesafe/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.mergesafe/mergesafe)Source: MCP Registry · repository. Synced Nov 20, 2026, 21:17 UTC.
MergeSafe MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the MergeSafe MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 11 of which can change, send or delete something, and 0 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 MergeSafe MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: answer_finding and end_session.
Can the MergeSafe MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: review_local.
What tools does the MergeSafe MCP server have?
- 16 tools: 2 destructive, 1 irreversible, 8 write, 5 read. answer_finding, end_session, review_local, request_review, request_review_with_context, start_session, review_branch, confirm_review and 8 more.
Does the MergeSafe MCP server need sign-in or OAuth?
- Yes. Its remote endpoint answered 401 without credentials, and it publishes OAuth protected resource metadata (RFC 9728); its authorization server supports dynamic client registration.
Does the MergeSafe MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): review_local.
Has the MergeSafe MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.