Openllmetry JsBLOCK
Sister project to OpenLLMetry, but in Typescript. Open-source observability for your LLM application, based on OpenTelemetry
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
For Javascript / Typescript
Open-source observability for your LLM application
Get started with Node.js or Next.js »
Slack | Docs | Website
7509fa42b18bOBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add node-server-sdk --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID} --env AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY} --env COHERE_API_KEY=${COHERE_API_KEY} -- npx -y @traceloop/[email protected]{
"mcpServers": {
"node-server-sdk": {
"command": "npx",
"args": [
"-y",
"@traceloop/[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"AWS_ACCESS_KEY_ID": "${AWS_ACCESS_KEY_ID}",
"AWS_SECRET_ACCESS_KEY": "${AWS_SECRET_ACCESS_KEY}",
"COHERE_API_KEY": "${COHERE_API_KEY}"
}
}
}
}Exposed tools (23)
22 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add | write | Add two numbers together |
attachment-test-dataset | read | Dataset for testing attachments |
calculateDistance | read | Calculate distance between two cities |
divideNumbers | read | Use this function to divide two numbers |
error-test-1234 | read | Temporary dataset for error testing |
error-test-5678 | read | Temporary dataset for error testing |
getWeather | read | Get the current weather for a specified location |
get_cities_data_by_country | read | Get city population data by country |
get_current_weather | read | Get the current weather in a given location |
get_tomorrow_weather | read | Get tomorrow |
get_weather | read | Returns current weather |
lookup | read | Look up data |
multiply | read | Multiply two numbers |
objectTool | read | Tool from object |
search | read | Search the web |
searchRestaurants | read | Search for restaurants in a location |
sumNumbers | read | Use this function to sum two numbers |
test-dataset-comprehensive-example | read | Comprehensive test dataset |
testTool | read | Test tool |
test_tool | read | |
toolWithStringParams | read | Tool with pre-stringified parameters |
v4Tool | read | v4 format tool |
v5Tool | read | v5 format tool |
Trust audit
BLOCKgrade F · trust 48/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (5 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
"Token: ghp_aBcDeFgHiJkLmNoPqRsTuVwXyZ123456789abc",
const result = eval(sanitized);
const result = eval(sanitized);
const result = eval(sanitized);
"text": "{\"id\":\"msg_018V3xGyrq6nc25GVuWiaKHx\",\"type\":\"message\",\"role\":\"assistant\",\"model\":\"claude-opus-4-1-20250805\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"This is a very s"text": "AAAB+wAAAEtwlPWYCzpldmVudC10eXBlBwAFY2h1bmsNOmNvbnRlbnQtdHlwZQcAEGFwcGxpY2F0aW9uL2pzb24NOm1lc3NhZ2UtdHlwZQcABWV2ZW50eyJieXRlcyI6ImV5SnZkWFJ3ZFhSVVpYaDBJam9pWEc1VWFHVWdabTkxY2lCallYSmthVzVoYkN
"text": "AAAArwAAAEt2W082CzpldmVudC10eXBlBwAFY2h1bmsNOmNvbnRlbnQtdHlwZQcAEGFwcGxpY2F0aW9uL2pzb24NOm1lc3NhZ2UtdHlwZQcABWV2ZW50eyJieXRlcyI6ImV5SmpiMjF3YkdWMGFXOXVJam9pSUZSb1pTSXNJbk4wYjNCZmNtVmhjMjl1SWp
"text": "AAAFowAAAEvjZjOECzpldmVudC10eXBlBwAFY2h1bmsNOmNvbnRlbnQtdHlwZQcAEGFwcGxpY2F0aW9uL2pzb24NOm1lc3NhZ2UtdHlwZQcABWV2ZW50eyJieXRlcyI6ImV5Sm5aVzVsY21GMGFXOXVjeUk2VzNzaVptbHVhWE5vWDNKbFlYTnZiaUk2SWt
"text": "AAAA3wAAAEuPia/5CzpldmVudC10eXBlBwAFY2h1bmsNOmNvbnRlbnQtdHlwZQcAEGFwcGxpY2F0aW9uL2pzb24NOm1lc3NhZ2UtdHlwZQcABWV2ZW50eyJieXRlcyI6ImV5Sm5aVzVsY21GMGFXOXVJam9pWEc0aUxDSndjbTl0Y0hSZmRHOXJaVzVmWTI
.prettierignore
.prettierignore
.prettierignore
.prettierignore
.prettierignore
const rootConfig = require("../../eslint.config.cjs");const rootConfig = require("../../eslint.config.cjs");const rootConfig = require("../../eslint.config.cjs");const rootConfig = require("../../eslint.config.cjs");const rootConfig = require("../../eslint.config.cjs");url: "http://127.0.0.1:6333",
Cannot connect to the Docker daemon at unix:///var/run/docker.sock. Is the docker daemon running?
@apidevtools/swagger-parser, @types/node, openapi-types, openapi-typescript, ts-node, @commitlint/cli, @commitlint/config-conventional, @eslint/eslintrc
@opentelemetry/api, @opentelemetry/semantic-conventions
@opentelemetry/api, @opentelemetry/core, @opentelemetry/instrumentation, @opentelemetry/semantic-conventions, tslib, @anthropic-ai/sdk, @opentelemetry/context-async-hooks, @opentelemetry/sdk-trace-nod
@opentelemetry/api, @opentelemetry/core, @opentelemetry/instrumentation, @opentelemetry/semantic-conventions, tslib, @aws-sdk/client-bedrock-runtime, @opentelemetry/context-async-hooks, @opentelemetry
Gates applied: critical_finding, no_behavioural_pass.
7509fa42b18bfull audit observations/trust-audit/mcp-server/traceloop__openllmetry-js.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 7509fa42b18b | BLOCK | F | 48 | first audit |
Questions
What is the @traceloop/instrumentation-mcp MCP server?
Sister project to OpenLLMetry, but in Typescript. Open-source observability for your LLM application, based on OpenTelemetry
What tools does @traceloop/instrumentation-mcp expose?
23 in total: 22 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @traceloop/instrumentation-mcp safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (48/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does @traceloop/instrumentation-mcp need?
It reads ANTHROPIC_API_KEY, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, COHERE_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY, OPENAI_API_KEY, PINECONE_API_KEY, TOGETHER_API_KEY, TRACELOOP_API_KEY and TRACELOOP_ENRICH_TOKENS from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (7509fa42b18b), read on 2026-10-12. The repository is watched and re-audited when it changes.