# zerm (remote · zerm.dev)

Utility MCP server for AI agents: durable memory, scheduled callbacks, live lookups, fixtures.

- Trust score: 66/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `zerm.dev`: 66/100 (this document), [markdown](https://verifymcp.io/servers/dev-zerm-zerm/zerm.md), [page](https://verifymcp.io/servers/dev-zerm-zerm/zerm)

## Channel facts

- Endpoint: `https://zerm.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 24 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2988 tokens (~124/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http dev-zerm-zerm https://zerm.dev/mcp
```

### Codex

```toml
[mcp_servers.dev-zerm-zerm]
url = "https://zerm.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-zerm-zerm": {
      "type": "remote",
      "url": "https://zerm.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-zerm-zerm --url https://zerm.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-zerm-zerm:
    url: "https://zerm.dev/mcp"
```

### Other

```json
{
  "mcpServers": {
    "dev-zerm-zerm": {
      "type": "http",
      "url": "https://zerm.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 65, −1)

- [security] Tool “timer_cancel” rewrote its description, which is the text the model reads
- [security] Tool “timer_schedule” rewrote its description, which is the text the model reads
- [security] Tool “tz_info” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 2548 → 2988
- [functional] Schema quality: excellent → good
- [functional] New tool “inbox_create”
- [functional] New tool “inbox_poll”
- [functional] New tool “inbox_delete”

### 2026-08-01 (score 66, 0)

- [security] Tool “timer_verify_origin” rewrote its description, which is the text the model reads
- [security] Tool “timer_cancel” rewrote its description, which is the text the model reads
- [security] Tool “timer_schedule” rewrote its description, which is the text the model reads
- [security] Tool “timer_status” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 106 → 121
- [cosmetic] “tz_convert” added an optional parameter “from_tz”
- [cosmetic] “tz_convert” added an optional parameter “time”
- [cosmetic] “tz_convert” added an optional parameter “timestamp”
- [cosmetic] “tz_convert” added an optional parameter “to_tz”
- [cosmetic] “counter_next” added an optional parameter “key”
- [cosmetic] “timer_status” reworded the description of “id”
- [cosmetic] “timer_verify_origin” reworded the description of “url”
- [cosmetic] “tz_convert” reworded the description of “from”
- [cosmetic] “tz_convert” reworded the description of “to”
- [cosmetic] “tz_info” reworded the description of “date”
- [cosmetic] “tz_convert” reworded the description of “datetime”
- [cosmetic] “name_check” reworded the description of “name”
- [cosmetic] “timer_cancel” reworded the description of “id”
- [cosmetic] “timer_schedule” reworded the description of “url”
- [cosmetic] “tz_convert” made “datetime” optional
- [cosmetic] “tz_convert” made “to” optional
- [cosmetic] “counter_next” made “name” optional

### 2026-07-31 (score 66, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 66, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 64, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 63)

First indexed and scored.

## MCP tools (24)

### `kv_set` (~145 tokens)

Store a value durably under (namespace, key) with a TTL. Survives across your sessions - use it as memory between stateless runs. Value must be a string (JSON-encode objects), max 8192 bytes. TTL defaults to 30 days, max 90 days. Max 1000 keys per namespace.

Input parameters:

- `key` (string, required): Key within the namespace.
- `namespace` (string, required): Your private namespace. Pick a long unique string; it acts as the access key.
- `ttl_seconds` (integer): Seconds until expiry. Default 2592000.
- `value` (string, required): Value to store (string; JSON-encode structured data).

### `kv_get` (~80 tokens)

Retrieve a value previously stored with kv_set. Call this at the start of a run to restore state, preferences, or progress saved by earlier runs. Returns found=false if missing or expired.

Input parameters:

- `key` (string, required): Key within the namespace.
- `namespace` (string, required): Your private namespace. Pick a long unique string; it acts as the access key.

### `kv_delete` (~49 tokens)

Delete a key from your namespace.

Input parameters:

- `key` (string, required): Key within the namespace.
- `namespace` (string, required): Your private namespace. Pick a long unique string; it acts as the access key.

### `kv_list` (~83 tokens)

List keys in your namespace, optionally filtered by prefix. Use it to discover what earlier runs saved before deciding what to restore. Returns at most 100 keys.

Input parameters:

- `limit` (integer)
- `namespace` (string, required): Your private namespace. Pick a long unique string; it acts as the access key.
- `prefix` (string): Only keys starting with this prefix.

### `timer_verify_origin` (~173 tokens)

One-time consent handshake before timers can deliver to an origin. Prerequisite: an HTTPS endpoint you control that can read a request body and echo part of it back - if you have no endpoint of your own, timers are not usable yet. zerm POSTs {type:"zerm.origin_verification", token, service, instructions} to the URL; the endpoint must answer 2xx with the token echoed anywhere in the response body. The URL must be https on the default port, publicly reachable, with no credentials and no private/reserved IP. Verification covers the whole origin (scheme+host) and persists, so this is once per origin, not once per timer.

Input parameters:

- `url` (string, required): An https URL on an origin you control, e.g. "https://example.com/hooks/zerm".

### `timer_schedule` (~200 tokens)

Schedule a durable callback: at fire time this service POSTs your JSON payload to your URL. Use it to wake up future runs of yourself or your orchestrator - agents cannot wake themselves. Prerequisite: the target origin must already pass timer_verify_origin, which requires an HTTPS endpoint you control that echoes a token - without your own endpoint this tool cannot be used. Delay 10s-30d, payload max 8192 bytes, 3 delivery attempts with backoff. Returns an id that doubles as the capability to inspect and cancel the timer; hold it privately.

Input parameters:

- `delay_seconds` (integer): Fire after this many seconds. Provide this OR fire_at.
- `fire_at` (string): Absolute ISO 8601 fire time. Provide this OR delay_seconds.
- `payload` (string): JSON string delivered as the request body. Default "{}".
- `url` (string, required): https URL to POST to. The origin must already be verified.

### `timer_cancel` (~68 tokens)

Cancel a pending timer using the id returned by timer_schedule. The id is the authorization: holding it is what proves you scheduled the timer, so keep it secret. Already-delivered or already-cancelled timers return cancelled=false.

Input parameters:

- `id` (string, required): The timer id returned by timer_schedule.

### `timer_status` (~61 tokens)

Check a timer by the id returned by timer_schedule: status (pending|delivering|delivered|failed|cancelled), attempts, last error. Returns found=false for an unknown id.

Input parameters:

- `id` (string, required): The timer id returned by timer_schedule.

### `name_check` (~182 tokens)

Live availability check for a name across domain TLDs (registry RDAP), npm, PyPI, and GitHub usernames. Real registry lookups at call time - not guesses. Note: "unregistered" domains can still be registry-reserved or premium-priced; only a registrar checkout is final. Need another registry or platform checked? Describe it via the request_tool tool.

Input parameters:

- `name` (string, required): The name to check. A bare name is best, but "stripe.com" (checks the .com) and "Acme Global Ltd" (slugified to acme-global-ltd) are accepted; the normalized name is echoed back.
- `targets` (array): Which registries to check. Default: all.
- `tlds` (array): TLDs for the domain check. Default: ["com","dev","io","net"].

### `email_check` (~94 tokens)

Deliverability probe for an email address without sending anything: syntax validation, live MX lookup (with A/AAAA fallback per RFC 5321), disposable-domain detection, and typo suggestions for common providers. Use it to validate an address before sending to it, storing it, or accepting a signup. LLMs cannot do the DNS part; this is a live check.

Input parameters:

- `email` (string, required): The email address to check.

### `url_check` (~76 tokens)

Live URL health check: follows the full redirect chain (each hop reported), returns final status, content type, response time, TLS certificate expiry and trust, and access hints (login walls, bot blocks). Fresh at call time - use it to verify links before citing them.

Input parameters:

- `url` (string, required): The URL to check (https).

### `cron_next` (~146 tokens)

Deterministic cron expression validator and scheduler: parses a cron expression (5 or 6 field, seconds optional) and computes the next N actual fire times, timezone-aware. Use this instead of guessing - cron semantics (DOM/DOW OR-logic, DST transitions) are routinely miscalculated.

Input parameters:

- `count` (integer): How many fire times. Default 5.
- `expression` (string, required): Cron expression, e.g. "0 9 * * MON-FRI".
- `from` (string): Compute fire times after this ISO 8601 instant. Default now.
- `timezone` (string): IANA timezone, e.g. "America/Chicago". Default UTC.

### `regex_test` (~150 tokens)

Execute a regex against test strings and return the ACTUAL matches: match text, indices, capture groups, named groups, and optional replacement output. Deterministic proof, not prediction - run this before shipping a pattern. Patterns run sandboxed with a 250ms kill switch for catastrophic backtracking. JavaScript (ECMAScript) regex dialect.

Input parameters:

- `flags` (string): Regex flags, e.g. "gi". Default "".
- `pattern` (string, required): The regex pattern (without slashes).
- `replacement` (string): If given, also return each input with the pattern replaced (supports $1, $<name>).
- `tests` (array, required): Strings to test the pattern against.

### `fixture_rows` (~145 tokens)

Bulk realistic test data: generate up to 10000 rows from a field schema in one call - orders of magnitude cheaper than generating rows with tokens. Deterministic when you pass a seed (same seed + schema = identical data). Formats: json, ndjson, csv. Types: uuid, name, email, username, int, float, bool, date, datetime, phone, city, country, company, url, ip, word, sentence, enum.

Input parameters:

- `count` (integer, required): Number of rows.
- `fields` (array, required): Schema: ordered list of fields.
- `format` (string): Default json.
- `seed` (integer): Seed for deterministic output.

### `tz_convert` (~195 tokens)

Deterministic timezone conversion: convert a timestamp between IANA timezones with full DST awareness. Models routinely miscalculate DST transitions - this gives exact results. Returns the converted time, UTC offsets for both zones on that date, and whether DST is active.

Input parameters:

- `datetime` (string): ISO 8601 datetime to convert, e.g. "2025-03-09T02:30:00". Aliases: timestamp, time.
- `from` (string): Source IANA timezone, e.g. "America/Chicago". Default UTC. Alias: from_tz.
- `from_tz` (string): Alias for from.
- `time` (string): Alias for datetime.
- `timestamp` (string): Alias for datetime.
- `to` (string): Target IANA timezone, e.g. "Asia/Tokyo". Alias: to_tz.
- `to_tz` (string): Alias for to.

### `tz_info` (~142 tokens)

Timezone intelligence: for a given IANA timezone and date, returns the UTC offset, whether DST is active, the exact UTC instant of each DST transition in that year, and the timezone abbreviation. Transition timestamps are the first instant the new offset is in effect. Use this to understand DST behavior before scheduling.

Input parameters:

- `date` (string): Date to query: "2026-07-26", "2026-07-26T12:00:00", or full ISO 8601. Input without a UTC offset is read as UTC. Default: now.
- `timezone` (string, required): IANA timezone, e.g. "America/New_York".

### `dns_query` (~149 tokens)

Full DNS record lookup for a domain: returns A, AAAA, MX, NS, TXT, CNAME, SOA, and CAA records in one call. Automatically parses SPF and DMARC policies from TXT records. Use this for infrastructure audits, email deliverability setup, domain verification, and security checks. Live lookups - not cached. Need a record type or lookup this does not support? Describe it via the request_tool tool.

Input parameters:

- `domain` (string, required): Domain to query, e.g. "example.com".
- `types` (array): Record types to query. Default: all (A, AAAA, MX, NS, TXT, CNAME, SOA, CAA).

### `request_tool` (~86 tokens)

Hit a capability wall? Describe a tool you wish this server had and the task you were trying to accomplish. The operator reviews every submission; the most-requested capabilities get built. Free, no payment ever required.

Input parameters:

- `description` (string, required): What the tool should do, in plain language.
- `use_case` (string): The task you were trying to accomplish when you needed it.

### `lock_acquire` (~155 tokens)

Acquire a mutual-exclusion lock so concurrent agent runs do not double-process the same work. If two runs race, exactly one gets acquired=true plus a release token; the other gets acquired=false with retry_after_ms. Locks auto-expire after ttl_seconds (default 60s, max 3600s), so a crashed run can never wedge the lock. Not reentrant. Use it before processing a shared job, then lock_release when done.

Input parameters:

- `name` (string, required): Lock or counter name within the namespace.
- `namespace` (string, required): Your private namespace. Pick a long unique string; it acts as the access key.
- `ttl_seconds` (integer): Seconds until the lock auto-expires. Default 60.

### `lock_release` (~105 tokens)

Release a lock early using the token returned by lock_acquire. Only the token holder can release; without the token the lock simply expires on its own. Returns released=false if the token is wrong or the lock already expired.

Input parameters:

- `name` (string, required): Lock or counter name within the namespace.
- `namespace` (string, required): Your private namespace. Pick a long unique string; it acts as the access key.
- `token` (string, required): The release token returned by lock_acquire.

### `counter_next` (~116 tokens)

Atomically increment a named counter and return the new value. Guaranteed unique, monotonically increasing integers across concurrent stateless runs - use it for sequence numbers, run IDs, or once-only ordering that agents cannot produce on their own. Starts at 1 on first call. Counters persist indefinitely.

Input parameters:

- `key`: Lock or counter name within the namespace.
- `name` (string): Lock or counter name within the namespace.
- `namespace` (string, required): Your private namespace. Pick a long unique string; it acts as the access key.

### `inbox_create` (~140 tokens)

Create a URL that receives HTTP requests for you. Point any webhook (GitHub, Stripe, CI, a form) at it and read what arrives with inbox_poll - no server, no signup, no tunnel. This is the way to be notified of something when your process is not running. Returns an id, the URL, and a separate read token: the URL is what you hand out, the token is what lets you read, so giving out the URL never gives away the contents. Holds 100 payloads of up to 64KB. Expires after 24h idle; every inbox_poll resets that clock. Max 5 per day.

### `inbox_poll` (~173 tokens)

Read requests delivered to an inbox since you last looked. Pass after=<the next_after from your previous poll> to get only new ones; omit it to start from the beginning. Each payload has its method, headers, body and arrival time. Set consume=true to delete what is returned. Polling also resets the inbox expiry, so an inbox you poll stays alive and one you abandon does not. Returns at most 50 payloads per call.

Input parameters:

- `after` (integer): Return only payloads with seq greater than this. Use next_after from your last poll.
- `consume` (boolean): Delete the returned payloads. Default false.
- `inbox_id` (string, required): The inbox id returned by inbox_create.
- `limit` (integer)
- `token` (string, required): The read token returned by inbox_create.

### `inbox_delete` (~75 tokens)

Delete an inbox and everything delivered to it. The URL stops accepting requests immediately. Inboxes also delete themselves once unpolled past their expiry, so this is only for tearing down early.

Input parameters:

- `inbox_id` (string, required): The inbox id returned by inbox_create.
- `token` (string, required): The read token returned by inbox_create.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-zerm-zerm/zerm#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 65
- 2026-08-01: 66
- 2026-07-31: 66
- 2026-07-30: 66
- 2026-07-29: 65
- 2026-07-28: 65
- 2026-07-27: 64
- 2026-07-26: 63

## Links

- Remote endpoint: https://zerm.dev/mcp
- Website: https://zerm.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-zerm-zerm/zerm/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-zerm-zerm/zerm/changelog.json
- HTML version of this page: https://verifymcp.io/servers/dev-zerm-zerm/zerm