io.github.qmediat/cursor-mcp
NPM · @QMEDIAT.IO/CURSOR-MCP
Cursor's agent (cursor-agent CLI) through MCP: any model your plan offers, resumable sessions.
Available components
Last scanned (18 hours ago)
Scores higher than 82% of npm servers
Category Developer Tools
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 Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 1.30.1, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to qmediat/cursor-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 15 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 602 tokens (~120/item across 5 items; 5 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 Management67
- Stability observed for 20 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
- Structured output schemas are declared (40% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "cursor_agent" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 5 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.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 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.
- 26 Oct 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.
- 24 Oct 26 0
- CVE-2023-54404 affects this package: high ▼ security
- 23 Oct 26 +4
- Stability: unverified → 0.27 ▲ functional
- 21 Oct 26 0
- CVE-2026-111771 affects this package: high ▼ security
- CVE-2026-111768 affects this package: high ▼ security
- CVE-2026-111769 affects this package: high ▼ security
- CVE-2026-111767 affects this package: high ▼ security
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/@qmediat.io/cursor-mcp@1.2.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | qmediat/cursor-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/qmediat/cursor-mcp/.github/workflows/release.yml@refs/tags/v1.2.0 |
| Rekor log index | 3036170268 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:d40a7fb554ddd1b873f68d9c863f177f507433da91266a4a4c2ad09884a4cb03028931115dc83a19e507291184439492c4b94ced69b9cc61b2b107bb7 |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 6 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-22jm-h49p-29qw | CVE-2026-111767 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:L | yes |
| GHSA-46jr-4wx8-v453 | CVE-2026-111768 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-6prh-2h8m-c8cw | CVE-2026-111769 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:L/A:N | yes |
| GHSA-6qxp-vccf-f47h | CVE-2026-104850 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | yes |
| GHSA-rvq5-wwqv-78pq | CVE-2026-111771 | medium | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| 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 →
cursor_agent ~342
Execute a prompt using Cursor's AI agent with any model id the installed cursor-agent accepts (Composer, Claude, GPT, Gemini, Grok families on your plan; run cursor_models for ids). Modes: 'agent' (tools, terminal, search), 'plan' (design-focused), 'ask' (read-only). In headless mode cursor-agent only PROPOSES file changes unless the server operator set CURSOR_ALLOW_YOLO=true (then --force applies them; CURSOR_SANDBOX=enabled confines them). The result lists the files changed and the model used; a client that sends a progress token gets a progress notification per tool call.
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | Agent mode. 'agent' = full capabilities (file edit, terminal, search). 'plan' = design-focused, asks clarifying questions. 'ask' = read-only exploration. Default: agent. |
| model | string | – | AI model id as cursor-agent accepts it, passed through to --model (any id cursor_models lists; e.g. a Composer, Claude, GPT, Gemini or Grok id on your plan). Default: auto (Cursor picks the model). W… |
| prompt | string | yes | The prompt or task for the Cursor agent. Supports natural language instructions for code generation, review, debugging, and more. |
| timeout_seconds | integer | – | Maximum execution time in seconds (10-3600). Default: 600 (10 minutes). |
| workspace | string | – | Working directory for the agent. Affects file search scope and project context. Default: server's current working directory. |
| Name | Type | Req | Description |
|---|---|---|---|
| duration_ms | number|null | yes | – |
| exit_code | – | yes | cursor-agent's exit code (null when it was killed) |
| files_changed | array | yes | Paths of file-tool write/edit/delete calls that reported success, in order, each once. Shell commands are not inspected: a file written by a shell tool is not listed. |
| files_proposed | array | yes | Paths of file-tool write/edit/delete calls that did not report success (proposed without --force, refused, failed), each once |
| is_error | boolean | yes | – |
| model | string|null | yes | The model cursor-agent reported at start (its display name), if it did |
| noise_lines | integer | yes | stdout lines that were not stream-json events (counted, never dropped) |
| noise_sample | array | yes | The first few of those lines, verbatim (500 characters each at most) |
| request_id | string|null | yes | – |
| result | string | yes | The agent's final answer; without a result event, its last message, else empty (what stdout held is in noise_sample, never here) |
| session_id | string|null | yes | The session to resume with cursor_reply |
| status | string | yes | cursor-agent's result subtype: success, error, …; no-result-event when the run ended without one |
| stderr | string|null | yes | – |
| tool_calls | integer | yes | Completed tool calls the agent made |
No examples provided.
cursor_health ~30
Check Cursor CLI installation, authentication, and server configuration. Run this first to verify everything is set up correctly.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
cursor_models ~56
List the model ids the installed cursor-agent offers (its `models` command), or a known list when it offers none. Pricing is on cursor.com/docs/models-and-pricing. Use an id with cursor_agent's 'model' parameter.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
cursor_reply ~135
Continue an existing Cursor agent session. Send a follow-up message in the same conversation context. Requires a session_id from a previous cursor_agent call.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | – | Override the model for this reply (any id cursor_models lists). If omitted, uses the session's original model. |
| prompt | string | yes | Follow-up message to send in an existing Cursor agent session. |
| session_id | string | yes | Session ID from a previous cursor-agent call. Use cursor-sessions to list available sessions. |
| timeout_seconds | integer | – | Maximum execution time in seconds (10-3600). Default: 600 (10 minutes). |
| Name | Type | Req | Description |
|---|---|---|---|
| duration_ms | number|null | yes | – |
| exit_code | – | yes | cursor-agent's exit code (null when it was killed) |
| files_changed | array | yes | Paths of file-tool write/edit/delete calls that reported success, in order, each once. Shell commands are not inspected: a file written by a shell tool is not listed. |
| files_proposed | array | yes | Paths of file-tool write/edit/delete calls that did not report success (proposed without --force, refused, failed), each once |
| is_error | boolean | yes | – |
| model | string|null | yes | The model cursor-agent reported at start (its display name), if it did |
| noise_lines | integer | yes | stdout lines that were not stream-json events (counted, never dropped) |
| noise_sample | array | yes | The first few of those lines, verbatim (500 characters each at most) |
| request_id | string|null | yes | – |
| result | string | yes | The agent's final answer; without a result event, its last message, else empty (what stdout held is in noise_sample, never here) |
| session_id | string|null | yes | The session to resume with cursor_reply |
| status | string | yes | cursor-agent's result subtype: success, error, …; no-result-event when the run ended without one |
| stderr | string|null | yes | – |
| tool_calls | integer | yes | Completed tool calls the agent made |
No examples provided.
cursor_sessions ~39
List Cursor agent sessions created during this MCP server instance. Shows session IDs, models, and prompts. Use session IDs with cursor_reply to continue a conversation.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the io.github.qmediat/cursor-mcp server?
io.github.qmediat/cursor-mcp runs locally as an npm package, launched with npx -y @qmediat.io/cursor-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 · @qmediat.io/cursor-mcp
claude mcp add qmediat-cursor-mcp -- npx -y @qmediat.io/cursor-mcp
What is the io.github.qmediat/cursor-mcp server?
io.github.qmediat/cursor-mcp is listed in the public MCP registry as io.github.qmediat/cursor-mcp. Cursor's agent (cursor-agent CLI) through MCP: any model your plan offers, resumable sessions. This page covers its npm package (@qmediat.io/cursor-mcp).
Is the io.github.qmediat/cursor-mcp server safe to use?
io.github.qmediat/cursor-mcp scores 84 out of 100 on VerifyMCP. We recorded 6 known advisories against it as of 4 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 io.github.qmediat/cursor-mcp server expose?
io.github.qmediat/cursor-mcp exposes 5 tools: cursor_agent, cursor_reply, cursor_models, cursor_sessions, cursor_health. Their descriptions and schemas cost roughly 602 tokens of context every time the server is loaded.
Is the io.github.qmediat/cursor-mcp server still maintained?
io.github.qmediat/cursor-mcp 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.
What licence is the io.github.qmediat/cursor-mcp server under?
io.github.qmediat/cursor-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.