OnlyMCP
NPM · ONLYMCP · 2 COMPONENTS
Skills, agents and memory in the cloud, plus a gateway to your other MCP servers.
Available components
Last scanned (19 hours ago)
Scores higher than 31% of npm servers
Category Memory and Knowledge
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 Security93
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known medium-severity CVE affects glob 13.0.6, reached via cacache > glob. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 46 of 172 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
- Actively maintained (last published 2 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability60
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 1742 tokens (~58/item across 30 items; 30 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management47
- Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 31 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
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.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 −1
- CVE-2026-118764 affects this package: medium ▼ security
- CVE-2026-118773 affects this package: medium ▼ security
- Known CVEs: pass → fail ▼ security
- 29 Oct 26 +27
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.88 ▲ functional
- 28 Oct 26 −25
- Malware scan: pass → unverified ▼ security
- Known CVEs: pass → unverified ▼ security
- Schema quality: 1421 → 1742 ▼ functional
- Dependency health: 0.88 → unverified ▼ functional
- Package version: 0.21.0 → 0.22.0 functional
- Package version: 0.21.0 → 0.21.2 functional
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 24 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- Stability: unverified → 0.10 ▲ functional
- Package version: 0.20.0 → 0.21.0 functional
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 4 Nov 2026 · Analysed npm/onlymcp@0.22.0
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 →
Vulnerabilities 2 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-3g3m-2fjr-6pw4 | CVE-2026-118773 | medium | yes | |
| GHSA-g3hv-75wg-m249 | CVE-2026-118764 | medium | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 172 packages
| Packages resolved | 172 |
|---|---|
| Stale | 46 |
| 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 →
agent_delete Delete an agent ~42
Delete one agent. Moves it to the trash; it can be restored in the dashboard for the trash period (default 7 days).
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
No output schema declared.
No examples provided.
agent_write Write an agent ~63
Create an agent or replace an existing one. Leave model out to keep the one it already has.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | – |
| description | string | yes | – |
| model | string | – | – |
| name | string | yes | – |
| tools | array | – | – |
No output schema declared.
No examples provided.
connection_create Add a connection ~122
Connect a remote MCP server (http or sse only - a stdio server cannot be started on somebody else's behalf). It is probed straight away. Passing a secret here puts it into this conversation; leave it out and set it in the dashboard if that matters.
| Name | Type | Req | Description |
|---|---|---|---|
| authHeaderName | string | – | – |
| authType | string | yes | – |
| name | string | yes | – |
| secret | string | – | – |
| slug | string | yes | – |
| teamId | string | – | – |
| transport | string | yes | – |
| url | string | yes | – |
No output schema declared.
No examples provided.
connection_delete Delete a connection ~33
Disconnect a remote MCP server and forget its stored credential. Its tools disappear from the gateway.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
connection_tool_toggle Switch a connection tool on or off ~55
Switch one tool of a connected server on or off. A tool that is off costs no room in any client's tool list.
| Name | Type | Req | Description |
|---|---|---|---|
| enabled | boolean | yes | – |
| slug | string | yes | – |
| tool | string | yes | – |
No output schema declared.
No examples provided.
connection_tools List a connection's tools ~33
List what one connected server offers, and whether each tool is switched on for the gateway.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
connection_update Update a connection ~94
Change a connected MCP server. Only the fields you pass are touched; url, transport, authType and secret trigger a fresh probe.
| Name | Type | Req | Description |
|---|---|---|---|
| authHeaderName | string | – | – |
| authType | string | – | – |
| enabled | boolean | – | – |
| name | string | – | – |
| secret | string | – | – |
| slug | string | yes | – |
| transport | string | – | – |
| url | string | – | – |
No output schema declared.
No examples provided.
get_agent_definition Load an agent definition ~30
Delivers an agent's system prompt from the OnlyMCP cloud.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
No output schema declared.
No examples provided.
get_skill Load a skill ~35
Delivers a skill's full content from the OnlyMCP cloud. Called from the stub files.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
No output schema declared.
No examples provided.
get_skill_file Read a skill file ~69
Delivers a single companion file of a skill from the OnlyMCP cloud, e.g. references/palette.md. Usually not needed: `npx onlymcp sync` places these files next to the SKILL.md.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
| path | string | yes | – |
No output schema declared.
No examples provided.
list_agents List agents ~32
List every agent available to this user, with its description. Use when this client has no agent files of its own.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_connections List connections ~29
List the MCP servers connected through this OnlyMCP account, with the tool-name prefix each one uses.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_memory List memory files ~27
List the paths of every memory file in this account, private and team, sorted by path.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_skill_files List skill files ~30
List the companion files of one skill, with their size in bytes.
| Name | Type | Req | Description |
|---|---|---|---|
| skill | string | yes | – |
No output schema declared.
No examples provided.
list_skills List skills ~32
List every skill name available to this user. Use when a skill you need is not named in the server instructions.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_teams List teams ~33
List the teams this account is in, one per line: the team id, its name and your role in it.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
memory_append Append to a memory file ~56
Appends text to a memory file, after a newline when the file does not end with one. A missing file is created.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | – |
| ifMatch | string | – | – |
| path | string | yes | – |
No output schema declared.
No examples provided.
memory_delete Delete a memory file ~43
Delete one memory file. Moves it to the trash; it can be restored in the dashboard for the trash period (default 7 days).
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | – |
No output schema declared.
No examples provided.
memory_links Show memory links ~36
A memory file's [[links]], split between the ones that point somewhere and the ones that point nowhere.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | – |
No output schema declared.
No examples provided.
memory_move Move a memory file or folder ~61
Moves or renames a memory file. Every [[link]] that would no longer find it follows along, by name or by path, unless turned off.
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | yes | – |
| to | string | yes | – |
| updateLinks | boolean | – | – |
No output schema declared.
No examples provided.
memory_read Read a memory file ~78
Reads a memory file live from the OnlyMCP cloud. No disk cache. from (first line, counted from 1) and lines (how many, 1 to 2000) return a range and the total number of lines.
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | – | – |
| lines | string | – | – |
| path | string | yes | – |
No output schema declared.
No examples provided.
memory_search Search memory ~50
Full-text search across memory, skills and agents. Delivers the best hits with a short snippet each.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| query | string | yes | – |
| types | string | – | – |
No output schema declared.
No examples provided.
memory_tree Show the memory tree ~34
This account's folder structure: every folder, empty ones included, and the files in it.
| Name | Type | Req | Description |
|---|---|---|---|
| scope | string | – | – |
No output schema declared.
No examples provided.
memory_write Write a memory file ~45
Writes a memory file live into the OnlyMCP cloud (write-through).
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | – |
| ifMatch | string | – | – |
| path | string | yes | – |
No output schema declared.
No examples provided.
skill_delete Delete a skill ~49
Delete one skill and every file that belongs to it. Moves it to the trash; it can be restored in the dashboard for the trash period (default 7 days).
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
No output schema declared.
No examples provided.
skill_file_delete Delete a skill file ~36
Delete one companion file of a skill. The skill itself stays.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | – |
| skill | string | yes | – |
No output schema declared.
No examples provided.
skill_file_write Write a skill file ~58
Create or replace one companion file of a skill. Use encoding base64 for anything that is not text.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | – |
| encoding | string | yes | – |
| path | string | yes | – |
| skill | string | yes | – |
No output schema declared.
No examples provided.
skill_write Write a skill ~47
Create a skill or replace the body of an existing one. The body is the whole SKILL.md, frontmatter included.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | – |
| name | string | yes | – |
No output schema declared.
No examples provided.
team_return Return from a team ~92
Take an item out of a team and back under its owner. Name one of your own items, or pass the id of any item of the team if you may delete that kind of content there. The item keeps its owner, and the return is never refused on a quota.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | – | – |
| kind | string | yes | – |
| name | string | – | – |
| team | string | yes | – |
No output schema declared.
No examples provided.
team_share Share with a team ~85
Move one of your own memory files, skills or agents into a team, so its members can use it. You need the right to create that kind of content in the team, the team must not hold an item of that name already, and a frozen team takes nothing new.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | yes | – |
| name | string | yes | – |
| team | string | yes | – |
No output schema declared.
No examples provided.
How do I install the OnlyMCP MCP server?
OnlyMCP runs locally as an npm package, launched with npx -y onlymcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · onlymcp
claude mcp add com-only-mcp-onlymcp -- npx -y onlymcp
What is the OnlyMCP MCP server?
OnlyMCP is an MCP server listed in the public MCP registry as com.only-mcp/onlymcp. Skills, agents and memory in the cloud, plus a gateway to your other MCP servers. This page covers its npm package (onlymcp).
Is the OnlyMCP MCP server safe to use?
OnlyMCP scores 62 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 4 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 OnlyMCP MCP server expose?
OnlyMCP exposes 30 tools: memory_read, memory_write, memory_append, list_memory, memory_delete, and 25 more. Their descriptions and schemas cost roughly 1,529 tokens of context every time the server is loaded.
Is the OnlyMCP MCP server still maintained?
OnlyMCP is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.