Android Texter
NPM · ANDROID-TEXTER-MCP
Send and read SMS and MMS from your own Android phone and number via Android Texter.
Available components
Last scanned (1 day ago)
Scores higher than 56% of npm servers
Category Communication
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability68
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2617 tokens (~186/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
- Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 +12
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → pass ▲ functional
- 20 Nov 26 −11
- Known CVEs: pass → unverified ▼ security
- Schema quality: 154 → 186 ▼ functional
- Dependency health: pass → unverified ▼ functional
- Package version: 1.1.0 → 1.2.0 functional
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Nov 26 +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.
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Nov 26 +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.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/android-texter-mcp@1.2.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cancel_scheduled_message Cancel a scheduled message ~79
Cancel a message that is scheduled for a future send, so it never goes out. Only works while it is still pending; a message that has already been released to the phone cannot be recalled.
| Name | Type | Req | Description |
|---|---|---|---|
| message_id | string | yes | The id of the scheduled message, as returned by list_scheduled_messages or by send_message when it was scheduled. |
No output schema declared.
No examples provided.
get_conversation Read a conversation ~181
Read the messages in the conversation with one phone number, newest first. Each message has direction (inbound or outbound), body, status, created_at, and media_url for picture messages. For a group conversation, pass the thread_ref from list_conversations.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Messages per page, 1 to 100. Default 50. |
| page | number | – | Page number, 1 for the newest messages. Default 1. |
| phone | string | yes | The other party's phone number. Use E.164 format (e.g. +15551234567). A number without a country code is read in the country of the phone's SIM. |
| thread_ref | string | – | Optional. The conversation's thread_ref from list_conversations or a message. Required to read a group conversation; preferred over phone when known. |
No output schema declared.
No examples provided.
get_message_status Check a message's status ~67
Check where an outbound message is: queued (waiting for the phone), sent (the phone handed it to the carrier), delivered, or failed. Pass the message_id returned by send_message or send_broadcast.
| Name | Type | Req | Description |
|---|---|---|---|
| message_id | string | yes | The message id returned when it was sent. |
No output schema declared.
No examples provided.
known_issues Check what Android Texter already knows about ~134
Read Android Texter's own list of current limitations, plan limits and known bugs, with the workaround for each. Call this BEFORE telling the user that something is broken, impossible, or a bug, and before using report_issue: a 429 on a send, a status that never reaches 'delivered', and a broadcast that cannot be scheduled all have known explanations, and guessing at them in front of the user gets it wrong. Reads nothing about the account and sends nothing anywhere.
| Name | Type | Req | Description |
|---|---|---|---|
| tool | string | – | Optional. Only issues affecting this tool (e.g. send_broadcast), plus the ones that affect everything. |
No output schema declared.
No examples provided.
list_contact_tags List contact tags ~22
List every tag used on your contacts, for filtering list_contacts.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_contacts List contacts ~136
List or search your Android Texter contacts. Each contact has id, phone, name, email, company, notes, tags, and line type and carrier when a lookup has been run. Filter by tag to build a list for send_broadcast.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Contacts per page, 1 to 500. Default 50. |
| page | number | – | Page number. Default 1. |
| search | string | – | Optional. Matches phone, name, email, company, or carrier (case-insensitive substring). |
| tag | string | – | Optional. Only contacts carrying this exact tag. See list_contact_tags. |
No output schema declared.
No examples provided.
list_conversations List conversations ~145
List your text conversations, most recent activity first. Each entry has phone (the other party, or a group's members joined by commas), last_message, last_direction, last_at, message_count, thread_type (direct or group), thread_ref, and the device it is on. Use get_conversation to read one in full.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | How many conversations to return, 1 to 200. Default 20. |
| view | string | – | Which folder to list. all: everything except archived and spam (default). inbox: conversations where the other side has replied. outbox: nothing has come back yet. archived and spam: those folders on… |
No output schema declared.
No examples provided.
list_devices List paired phones ~84
List the Android phones paired to your Android Texter account. Each entry has its id, name, phone_number, status (online or offline), battery_level, last_seen, and its SIMs (slot, label, number) on dual-SIM phones. Texts are sent from these phones with their own numbers and carrier plans, so check that one is online before sending.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_scheduled_messages List scheduled messages ~51
List the messages that are scheduled to go out later and have not been sent or cancelled yet, soonest first. Use this before scheduling more, and to get the id needed by cancel_scheduled_message.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
report_issue Report a problem or limitation to Android Texter ~551
Tell Android Texter about something you could not do with these tools: a capability that is missing, a tool whose arguments or behaviour were unclear, a result that looked wrong, or a limit you hit on the user's behalf. Android Texter cannot see this from their logs, because the thing worth reporting is usually the request you decided not to make. Call known_issues first, so you do not report something already known. Use it when you have actually hit the wall, not speculatively, and once per problem: filing the same thing twice adds nothing. PRIVACY, and this is not optional: describe the PROBLEM, never the user's data. No message text, no phone numbers, no names, no email addresses, no contact details, not even as an example. The server strips them out and the report is worse for having had them. WHAT HAPPENS NEXT depends on a setting the account owner controls, and the reply tells you which: either it is saved as the owner's own draft and Android Texter cannot see it until the owner approves it, or it goes straight to Android Texter, or reports are turned off for this account. Read the reply's message back to the user in your own words, including the link, whichever it says. That reply is how the owner finds out this exists.
| Name | Type | Req | Description |
|---|---|---|---|
| blocked | boolean | – | True if you could not complete the user's request at all. False if you got there another way but it was awkward. This is the field that sorts the queue, so be honest about it. |
| category | string | yes | missing_capability: there is no tool for what was needed. unclear_tool: the tool exists but its arguments or behaviour were ambiguous. tool_error: it returned an error you could not act on. wrong_res… |
| expected | string | – | Optional. One sentence on what you expected to be able to do, or what you expected to happen. |
| goal | string | yes | One sentence on what you were trying to achieve, in terms of the task, not the data. Good: "schedule one broadcast to a tagged list for tomorrow morning". Bad: anything quoting a message, a number or… |
| suggestion | string | – | Optional. One sentence on what would have solved it, if you can name it (a tool, an argument, a clearer description). |
| tool | string | – | Optional. The tool this is about, e.g. send_broadcast. Leave out if it is about the API as a whole. |
No output schema declared.
No examples provided.
save_contact Create or update a contact ~166
Create a contact, or update the one that already has this phone number. Only the fields you pass are changed; fields you leave out keep their current values. Tags are added to the contact's existing tags, never removed.
| Name | Type | Req | Description |
|---|---|---|---|
| company | string | – | Optional company. |
| string | – | Optional email address. | |
| name | string | – | Optional name, used for {{name}} in send_broadcast. |
| notes | string | – | Optional notes. Replaces any existing notes. |
| phone | string | yes | The contact's phone number, which identifies the contact. Use E.164 format (e.g. +15551234567). A number without a country code is read in the country of the phone's SIM. |
| tags | array | – | Optional tags to add. |
No output schema declared.
No examples provided.
search_messages Search messages ~92
Search all of your texts, sent and received, for a word or phrase. Matches the message text, the phone number, and the contact's name. Newest first.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Results per page, 1 to 100. Default 50. |
| page | number | – | Page number. Default 1. |
| q | string | yes | What to search for (case-insensitive substring). |
No output schema declared.
No examples provided.
send_broadcast Send one text to many people ~343
Send the same text to a list of phone numbers (up to 500), each as its own one-to-one message from your paired phone's own number. Only use this when the user has asked to text a list of people, and confirm the list and wording first: every recipient gets a real text. The message can be personalized from each recipient's contact record with {{name}}, {{first_name}}, {{last_name}}, {{full_name}}, {{company}}, {{city}} or {{state}}, and {{first_name|there}} gives a fallback when the field is empty. {{name}} is the name set by save_contact; first_name and last_name are only filled for contacts imported with those fields. Broadcasts send now and cannot be scheduled. Returns sent and failed counts and a message_id per recipient.
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Optional id of the phone to send every message from. If omitted, the first online phone is used. |
| media_url | string | – | Optional public URL of an image to attach to every message (MMS). |
| message | string | yes | The text to send, up to 1600 characters. May contain the personalization tokens above. |
| phones | array | yes | Recipient phone numbers, up to 500. Use E.164 format (e.g. +15551234567). A number without a country code is read in the country of the phone's SIM. To text everyone with a tag, get their numbers fro… |
| round_robin | boolean | – | Optional. Spread the messages across all of your online phones instead of sending them all from one. Ignored when device_id is set. |
No output schema declared.
No examples provided.
send_message Send a text ~420
Send a text message from one of your paired Android phones, using that phone's own number and carrier plan, to a real person. Confirm the recipient and wording with the user before sending. The call returns once the message is queued and pushed to the phone, not when it is delivered: use get_message_status with the returned message_id to follow it. Pass scheduled_at to send it later instead of now. Free plans have a daily sending limit.
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Optional id of the phone to send from (see list_devices). If omitted, the first online phone is used. If none is online, it is queued for the first paired phone and fails if that phone does not come… |
| media_url | string | – | Optional public URL of an image to attach. Makes this a picture message (MMS). |
| message | string | yes | The text to send, up to 1600 characters. |
| phone | string | yes | The recipient's phone number. Use E.164 format (e.g. +15551234567). A number without a country code is read in the country of the phone's SIM. Several numbers separated by commas (up to 25) send one… |
| scheduled_at | string | – | Optional time to send it instead of now, as an ISO 8601 timestamp with a time zone (e.g. 2026-11-03T14:30:00Z or 2026-11-03T09:30:00-05:00). Must be in the future. The server releases it to the phone… |
| sim_slot | number | – | Optional, dual-SIM phones only: which SIM to send from, 0 for SIM 1 and 1 for SIM 2. If omitted, the phone uses the SIM chosen for that conversation, else the SIM the recipient last texted, else its… |
No output schema declared.
No examples provided.
How do I install the Android Texter MCP server?
Android Texter runs locally as an npm package, launched with npx -y android-texter-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · android-texter-mcp
claude mcp add argosautomation-android-texter -- npx -y android-texter-mcp
What is the Android Texter MCP server?
Android Texter is an MCP server listed in the public MCP registry as io.github.argosautomation/android-texter. Send and read SMS and MMS from your own Android phone and number via Android Texter. This page covers its npm package (android-texter-mcp).
Is the Android Texter MCP server safe to use?
Android Texter scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Android Texter MCP server expose?
Android Texter exposes 14 tools: list_devices, list_conversations, get_conversation, search_messages, send_message, and 9 more. Their descriptions and schemas cost roughly 2,471 tokens of context every time the server is loaded.
Is the Android Texter MCP server still maintained?
Android Texter is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Android Texter MCP server under?
Android Texter declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Android Texter MCP server?
VerifyMCP ran 16 checks on Android Texter, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.