io.github.cyanheads/mcp-ts-template
NPM · MCP-TS-TEMPLATE
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Available components
Last scanned (6 hours ago)
Scores higher than 38% 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 @opentelemetry/auto-instrumentations-node 0.71.0, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 80 of 349 dependencies flagged as unhealthy (8 deprecated). View diagnostics → Partial
Provenance & Transparency16
- Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Maintenance check failed: the publisher has marked this version as deprecated on the registry, telling users to stop installing it. See how to fix → Fail
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability86
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 582 tokens (~64/item across 9 items; 7 tools + 2 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management63
- Stability observed for 19 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 (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 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
- Supports UI / widget rendering.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.
- 5 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.
- 4 Nov 26 −6
- Stability: pass → 0.60 functional
- 31 Oct 26 0
- CVE-2026-118773 affects this package: high ▼ security
- CVE-2026-118764 affects this package: high ▼ security
- 29 Oct 26 0
- CVE-2026-118663 affects this package: high ▼ security
- Stability: 0.97 → pass security
- 28 Oct 26 0
- Stability: pass → 0.97 functional
- 22 Oct 26 0
- Stability: 0.97 → pass security
- 21 Oct 26 0
- Stability: pass → 0.97 functional
- 17 Oct 26 +47
- Injection markers: unverified → pass ▲ security
- Stability: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Schema quality: unverified → 100 ▲ 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 5 Nov 2026 · Analysed npm/mcp-ts-template@3.0.9
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 7 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-rmxm-3fg6-px4f | CVE-2026-118663 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N | yes |
| GHSA-q7rr-3cgh-j5r3 | CVE-2026-44902 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-8988-4f7v-96qf | CVE-2026-54285 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-qqmp-wf37-98f9 | CVE-2026-104872 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:N/A:N | yes |
| GHSA-45rx-2jwx-cxfr | CVE-2026-59892 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| 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 349 packages
| Packages resolved | 349 |
|---|---|
| Deprecated | 8 |
| Stale | 72 |
| 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 →
template_async_countdown Async Countdown (Task Demo) ~102
Demonstrates the MCP Tasks API with a countdown timer. When the client supports tasks, returns immediately with a task handle for polling. Otherwise, runs synchronously and returns the result directly.
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | – | Optional message to include in the final result |
| seconds | integer | yes | Number of seconds to count down (1-60) |
| simulateFailure | boolean | – | If true, simulates a failure at 50% progress (for testing) |
| Name | Type | Req | Description |
|---|---|---|---|
| completedAt | string | yes | ISO timestamp when countdown ended |
| duration | number | yes | Actual duration in milliseconds |
| message | string | yes | Completion or cancellation message |
| progress | number | yes | Final progress percentage (0-100) |
| startedAt | string | yes | ISO timestamp when countdown started |
| success | boolean | yes | Whether the countdown completed successfully |
| wasCancelled | boolean | yes | Whether the task was cancelled |
No examples provided.
template_cat_fact Template Cat Fact ~45
Fetches a random cat fact from a public API with an optional maximum length.
| Name | Type | Req | Description |
|---|---|---|---|
| maxLength | integer | – | Optional: The maximum character length of the cat fact to retrieve. |
| Name | Type | Req | Description |
|---|---|---|---|
| fact | string | yes | The retrieved cat fact. |
| length | integer | yes | The character length of the cat fact. |
| requestedMaxLength | integer | – | The maximum length that was requested for the fact. |
| timestamp | string | yes | ISO 8601 timestamp of when the response was generated. |
No examples provided.
template_code_review_sampling Code Review with Sampling ~100
Demonstrates MCP sampling by requesting an LLM to review code snippets. The tool uses the client's LLM to generate a code review summary.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The code snippet to review. |
| focus | string | – | The focus area for the code review. |
| language | string | – | Programming language of the code (e.g., "typescript", "python"). |
| maxTokens | integer | – | Maximum tokens for the LLM response. |
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The original code snippet. |
| focus | string | yes | The review focus area. |
| language | string | – | The programming language. |
| review | string | yes | The LLM-generated code review summary. |
| tokenUsage | object | – | Token usage information. |
No examples provided.
template_data_explorer Template Data Explorer ~64
Generates sample sales data and renders an interactive explorer. Users can sort columns, filter rows, and select entries directly in the UI. Hosts without MCP Apps support receive a text table.
| Name | Type | Req | Description |
|---|---|---|---|
| rowCount | integer | – | Number of sample rows to generate (5–100). |
| Name | Type | Req | Description |
|---|---|---|---|
| generatedAt | string | yes | ISO 8601 timestamp when data was generated. |
| rows | array | yes | Generated sales data rows. |
| summary | object | yes | Aggregate summary of the dataset. |
No examples provided.
template_echo_message Template Echo Message ~102
Echoes a message back with optional formatting and repetition.
| Name | Type | Req | Description |
|---|---|---|---|
| includeTimestamp | boolean | – | Whether to include an ISO 8601 timestamp in the response. |
| message | string | yes | The message to echo back. To trigger a test error, provide 'TRIGGER_ERROR'. |
| mode | string | – | How to format the message ('standard' | 'uppercase' | 'lowercase'). |
| repeat | integer | – | Number of times to repeat the formatted message. |
| Name | Type | Req | Description |
|---|---|---|---|
| formattedMessage | string | yes | The message after applying the specified formatting. |
| mode | string | yes | The formatting mode that was applied. |
| originalMessage | string | yes | The original message provided in the input. |
| repeatCount | integer | yes | The number of times the message was repeated. |
| repeatedMessage | string | yes | The final message repeated the requested number of times. |
| timestamp | string | – | Optional ISO 8601 timestamp of when the response was generated. |
No examples provided.
template_image_test Template Image Test ~52
Fetches a random cat image and returns it base64-encoded with the MIME type. Useful for testing image handling.
| Name | Type | Req | Description |
|---|---|---|---|
| trigger | boolean | – | A trigger to invoke the tool and fetch a new cat image. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | string | yes | Base64 encoded image data. |
| mimeType | string | yes | The MIME type of the image (e.g., 'image/jpeg'). |
No examples provided.
template_madlibs_elicitation Mad Libs Elicitation Game ~88
Plays a game of Mad Libs. If any parts of speech (noun, verb, adjective) are missing, it will use elicitation to ask the user for them.
| Name | Type | Req | Description |
|---|---|---|---|
| adjective | string | – | An adjective for the story. |
| noun | string | – | A noun for the story. |
| verb | string | – | A verb (past tense) for the story. |
| Name | Type | Req | Description |
|---|---|---|---|
| adjective | string | yes | The adjective used in the story. |
| noun | string | yes | The noun used in the story. |
| story | string | yes | The final, generated Mad Libs story. |
| verb | string | yes | The verb used in the story. |
No examples provided.
How do I install the io.github.cyanheads/mcp-ts-template server?
io.github.cyanheads/mcp-ts-template runs locally as an npm package, launched with npx -y mcp-ts-template. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · mcp-ts-template
claude mcp add cyanheads-mcp-ts-template -- npx -y mcp-ts-template
What is the io.github.cyanheads/mcp-ts-template server?
io.github.cyanheads/mcp-ts-template is listed in the public MCP registry as io.github.cyanheads/mcp-ts-template. TypeScript template for building MCP servers with declarative tooling, observability, and auth. This page covers its npm package (mcp-ts-template).
Is the io.github.cyanheads/mcp-ts-template server safe to use?
io.github.cyanheads/mcp-ts-template scores 70 out of 100 on VerifyMCP. We recorded 7 known advisories against it as of 5 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 io.github.cyanheads/mcp-ts-template server expose?
io.github.cyanheads/mcp-ts-template exposes 7 tools: template_cat_fact, template_code_review_sampling, template_echo_message, template_image_test, template_madlibs_elicitation, and 2 more. Their descriptions and schemas cost roughly 553 tokens of context every time the server is loaded.
Is the io.github.cyanheads/mcp-ts-template server still maintained?
io.github.cyanheads/mcp-ts-template is still listed as active in the MCP registry. We last reached this channel on 5 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.cyanheads/mcp-ts-template server under?
io.github.cyanheads/mcp-ts-template declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.