mcphost MCP server
dev.mcphost/mcphostmcphost.devstreamable-httpv0.130.19Scanned
Hosted MCP runtime where your agent publishes its own tools by tool call and keeps working.
18 tools: 2 do something that can't be undone, 9 change things and 7 only read.
- Reads private data · 3
- Reads text others write · 1
- Can send data out · 2
- 3 findings, 1 high
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here do 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 mcphost MCP server can do
The mcphost MCP server is published by mcphost.dev, a domain the MCP Registry verified. It has 18 tools. It can do things that cannot be undone, such as sending, paying or publishing (host.tool_publish and host.feedback.send) and create or change data (9 tools: signup, host.errors, host.redeem, billing.plans and 5 more), but cannot delete data. 7 tools only read.
3 tools read private data (host.quickstart, host.errors and host.whoami); 1 tool brings in text other people can write (host.errors); 2 tools can send data out of your system (host.tool_publish and host.feedback.send). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 3 findings, 1 of them high severity (model-directed-text and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 5 times since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 0.130.19.
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.
18 tools
Can't be undone 2Claude Code: ask
host.feedback.sendTell the host's humans what you needed: kind, up to 2048 bytes of text, optional context.Can send data outNo findings
Why it is in this group
- The name "host.feedback.send" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "host.feedback.send" says "send": it sends or publishes something to other people.
Description, as the server wrote it Tell the host's humans what you needed: kind, up to 2048 bytes of text, optional context. Works before signup. Returns feedback_id.
host.tool_publishPublish a tool of a registered kind (e.g.Can send data outNo findings
Why it is in this group
- The name "host.tool_publish" says "publish": a word for a change that another call does not undo.
What it can reach
- outboundThe name "host.tool_publish" says "publish": it sends or publishes something to other people.
Description, as the server wrote it Publish a tool of a registered kind (e.g. python, http or echo; the kind argument's enum lists them all) under this tenant's namespace. Call host.quickstart(kind) first for a filled-in example spec and the full publish-to-call sequence. Python's sandbox API: import mcphost (mcphost.table, mcphost.state, mcphost.docs). Name must match ^[a-z][a-z0-9_]{1,40}$; a rejection names the failing field and a corrected example. Try host.tool_test before a real call.
Changes things 9Claude Code: ask
billing.plansThe plan catalog (price and quotas per plan) and whether Stripe billing is configured on this host.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 The plan catalog (price and quotas per plan) and whether Stripe billing is configured on this host. Anonymous callers get the same answer as tenants.
host.errorsList every error code this host can return, each with its class (agent_fault | host_refusal | upstream_fault | plan_limit | host_fault), family, remedy, docs anchor, retryable flag…Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
What it can reach
- private-dataThe description's first sentence says "list" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "list" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it List every error code this host can return, each with its class (agent_fault | host_refusal | upstream_fault | plan_limit | host_fault), family, remedy, docs anchor, retryable flag and help_url -- the same object GET /errors.json serves. Pass code to get one row; a misspelt code answers tool_not_found with did_you_mean. Read-only, anonymous, no tenant data.
host.redeemExchange a signup(handoff: true) handoff_token for the tenant key it was issued for.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 Exchange a signup(handoff: true) handoff_token for the tenant key it was issued for. Single-use: a second redemption fails with handoff_token_redeemed; past its expiry it fails with handoff_token_expired. Unauthenticated -- the token itself is the proof.
host.resumeResume where you left off in one call (at most 4096 bytes): your tools with each one's last call status, unfinished runs, your newest notes, what changed on the host since your las…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 Resume where you left off in one call (at most 4096 bytes): your tools with each one's last call status, unfinished runs, your newest notes, what changed on the host since your last call, and one suggested next_call. truncated names any section that was cut -- call that section's own tool (host.tool.list, host.runs.list, host.note.list, host.changelog) for the rest. Read-only. An unauthenticated caller gets the onboarding block and creates no tenant.
host.state.setWrite one key in this tenant's key-value state namespace; value may be any JSON value.No findings
Why it is in this group
- The name "host.state.set" says "set": a word for a change.
Description, as the server wrote it Write one key in this tenant's key-value state namespace; value may be any JSON value. Overrun of the plan's state_bytes_max quota fails with state_quota_exceeded and writes nothing.
host.tool_callInvoke a tool this tenant has already published, by its local name -- the same real, metered call as calling it directly by its namespaced name (<namespace>.<name>), for a session …No findings
Why it is in this group
- The name "host.tool_call" says "call": a word for a change.
Description, as the server wrote it Invoke a tool this tenant has already published, by its local name -- the same real, metered call as calling it directly by its namespaced name (<namespace>.<name>), for a session that has no way to see its own namespaced tool name yet. Unlike host.tool_test, this counts toward host.usage and appears in host.tool_logs. Pass async: true for a tool that needs more than the call deadline: returns {run_id, status: "queued"} immediately instead of running inline -- see host.runs.get/wait. Pass version to pin the call to one of host.tool_history's versions instead of whichever is current.
host.tool_testDry-run a published tool by name: verdict (pass/will_fail/unverifiable), writes rolled back (dry_run); see host.quickstart.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 Dry-run a published tool by name: verdict (pass/will_fail/unverifiable), writes rolled back (dry_run); see host.quickstart.
signupExplicit signup, for a client that cannot keep a session across calls: create a tenant and receive a bearer key and namespace.2 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- High
The description contains "<secret>", a tag of the kind used to mark instructions for the model.
What this check looks forMatched text
description: "...enant implicitly and returns its own /u/<secret>/mcp URL in the response's onboarding fi..."
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...edeem call, if it leaks, carries a dead credential. The raw-key path (handoff omitted) sta..."
Description, as the server wrote it Explicit signup, for a client that cannot keep a session across calls: create a tenant and receive a bearer key and namespace. Unauthenticated. Most clients never need this -- any other host.*/billing.* call from a fresh connection creates a tenant implicitly and returns its own /u/<secret>/mcp URL in the response's onboarding field. Recommended here: pass handoff: true to receive a short-lived, single-use handoff_token instead of the raw key -- redeem it once with host.redeem to get the key, so a transcript of this call and the redeem call, if it leaks, carries a dead credential. The raw-key path (handoff omitted) stays fully supported.
Only reads 7Show 7 read-only tools
host.feedback.listList your own feedback (newest first, status received).No findings
Why it is in this group
- The name "host.feedback.list" says "list": a word for reading.
Description, as the server wrote it List your own feedback (newest first, status received). Anonymous callers get [].
host.help.getReturn the documentation section an anchor points at: its text (at most 4 KB) and its first fenced example.No findings
Why it is in this group
- The name "host.help.get" says "get": a word for reading.
Description, as the server wrote it Return the documentation section an anchor points at: its text (at most 4 KB) and its first fenced example. Pass an anchor exactly as an error, hint or help entry printed it, e.g. a rate_limited error's `anchor`. Read-only, anonymous, no tenant data. An unknown anchor is anchor_not_found with the nearest anchors in did_you_mean.
host.help.searchSearch this host's own documentation and tool descriptions.No findings
Why it is in this group
- The name "host.help.search" says "search": a word for reading.
Description, as the server wrote it Search this host's own documentation and tool descriptions. Returns up to k hits (default 3, response under 2 KB), each with a snippet, the nearest runnable example and an anchor. Read-only, anonymous, no tenant data -- call it with the error text or import line you are stuck on before reading any docs file.
host.quickstartReturn the shortest ordered sequence of calls to a working tool of `kind`, with your namespace and a filled-in example already substituted in, plus the current limits and a try_bef…Reads private dataNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "table": it reads databases.
Description, as the server wrote it Return the shortest ordered sequence of calls to a working tool of `kind`, with your namespace and a filled-in example already substituted in, plus the current limits and a try_before_call table naming the one dry-run tool for each case. Read-only -- this call alone never creates a tenant. Call this before host.tool_publish if you're not sure what a spec should look like. Unauthenticated callers get a worked example with no tenant data; any other host.*/billing.* call creates a tenant on first use, no signup required.
host.state.getRead one key from this tenant's key-value state namespace.No findings
Why it is in this group
- The name "host.state.get" says "get": a word for reading.
Description, as the server wrote it Read one key from this tenant's key-value state namespace. Returns found: false (not an error) if the key was never set.
host.state.listList keys (with their current values) in this tenant's key-value state namespace, optionally filtered by prefix.No findings
Why it is in this group
- The name "host.state.list" says "list": a word for reading.
Description, as the server wrote it List keys (with their current values) in this tenant's key-value state namespace, optionally filtered by prefix.
host.whoamiReturn the calling tenant's identity, including key_age_s and key_rotated_at for auditing credential hygiene.Reads private data1 finding
Why it is in this group
- The name "host.whoami" says "whoami": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "credential": it reads secrets.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...y_age_s and key_rotated_at for auditing credential hygiene."
Description, as the server wrote it Return the calling tenant's identity, including key_age_s and key_rotated_at for auditing credential hygiene.
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.
6 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 untrusted-input tool breaks every one.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__mcphost__host_errors"
]
}
}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, 18:52 UTC, unchanged since Oct 22, 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
- 11
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcphost.dev/.well-known/oauth-protected-resource
- Authorization servers
- https://mcphost.dev
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 11 tools that change things (2 irreversible, 9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcphost.dev/mcp: tools/list returned 18 tools to an anonymous client, including host.tool_publish (irreversible), host.feedback.send (irreversible), signup (write), host.errors (write), host.redeem (write) and 6 more
Findings
Matches of fixed checks, with the text they matched.
- Highsignup
The description contains "<secret>", a tag of the kind used to mark instructions for the model.
What this check looks forMatched text
description: "...enant implicitly and returns its own /u/<secret>/mcp URL in the response's onboarding fi..."
- Infosignup
The description mentions "credential".
What this check looks forMatched text
description: "...edeem call, if it leaks, carries a dead credential. The raw-key path (handoff omitted) sta..."
- Infohost.whoami
The description mentions "credential".
What this check looks forMatched text
description: "...y_age_s and key_rotated_at for auditing credential hygiene."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:host.tool_shareChanges thingsinputSchema
Tools1 changed.~1 changedView diff
- Changed:host.tool_publishCan't be undoneinputSchema
Tools1 changed.~1 changedView diff
- Changed:host.state.setChanges thingsinputSchema
Tools2 changed.~2 changedView diff
- Changed:host.feedback.sendCan't be undoneinputSchema
- Changed:host.tool_shareChanges thingsinputSchema
Tools1 changed.~1 changedView diff
- Changed:signupChanges thingsinputSchema
Install
Pinned to version 0.130.19. Values in angle brackets are yours to fill in.
claude mcp add --transport http mcphost https://mcphost.dev/mcpclaude mcp add --transport http mcphost https://mcphost.dev/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__mcphost__host_quickstart",
"mcp__mcphost__host_help_search",
"mcp__mcphost__host_help_get",
"mcp__mcphost__host_whoami",
"mcp__mcphost__host_state_get",
"mcp__mcphost__host_state_list",
"mcp__mcphost__host_feedback_list"
],
"ask": [
"mcp__mcphost__signup",
"mcp__mcphost__host_errors",
"mcp__mcphost__host_redeem",
"mcp__mcphost__billing_plans",
"mcp__mcphost__host_tool_publish",
"mcp__mcphost__host_tool_call",
"mcp__mcphost__host_tool_test",
"mcp__mcphost__host_state_set",
"mcp__mcphost__host_tool_share",
"mcp__mcphost__host_feedback_send",
"mcp__mcphost__host_resume"
],
"deny": []
}
}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 mcphost. Review it before you use it.
Capability tags behind 5 rules
- mcp__mcphost__host_quickstart private-data
- mcp__mcphost__host_errors private-data, untrusted-input
- mcp__mcphost__host_whoami private-data
- mcp__mcphost__host_tool_publish outbound
- mcp__mcphost__host_feedback_send outbound
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/dev.mcphost/mcphost/verify?hash=91b84c124436157726cc97c9b6b65c65be7256012d367dc94191e82d0be88d6d" | jq -e '.changed == false'Pinned hash 91b84c124436, from Nov 14, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.mcphost/mcphost/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.mcphost/mcphost)Source: MCP Registry · repository. Synced Nov 14, 2026, 13:17 UTC.
mcphost MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the mcphost MCP server safe?
- No scan can promise that. What its definitions show: 18 tools, 11 of which can change, send or delete something, and 3 findings (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the mcphost MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the mcphost MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: host.tool_publish and host.feedback.send.
What tools does the mcphost MCP server have?
- 18 tools: 2 irreversible, 9 write, 7 read. host.tool_publish, host.feedback.send, signup, host.errors, host.redeem, billing.plans, host.tool_call, host.tool_test and 10 more.
Does the mcphost MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the mcphost MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): host.tool_publish and host.feedback.send.
Has the mcphost MCP server changed its tools?
- Yes, 5 times since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.