# Reported issues for mcp-victoriametrics
Pod holds 17 of 20 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.
Back to [mcp-victoriametrics](/mcp/mcp-victoriametrics-victoriametrics-community).
## Most discussed
### Support dynamic per-request headers in tool calls
## Problem
`VM_INSTANCE_HEADERS` is static — set once at startup and cannot be changed during the MCP server's lifetime.
This doesn't work when headers need to be dynamic, for example short-lived auth tokens that expire and must be refreshed.
## Typical Scenario
VictoriaMetrics cluster deployed behind an auth proxy:
```
MCP Client → mcp-victoriametrics → Auth Proxy (validates X-Token) → vmselect
```
- The auth proxy requires a custom `X-Token` header on every request
- Tokens are short-liv
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/129) · 2026-03-04 · closed · external user · 13 comments
### Feature request: add otel-collector receivers metrics to metrics_metadata_db
Hi VM team,
we're using otel-collector to collect metrics from node, kubelet and k8s apiserver with following receivers:
- [hostmetricsreceiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/hostmetricsreceiver)
- [kubeletstatsreceiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/kubeletstatsreceiver)
- [k8sclusterreceiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/k8sclust
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/90) · 2025-11-07 · closed · external user · 10 comments
### Error running in streamable http mode
Hi Team,
While running the server in streamable http mode, getting below error:
**Error on server:**
`2025/09/15 05:53:18 Starting mcp-victoriametrics version dev (date: unknown)
2025/09/15 05:53:26 Starting server in HTTP mode on 0.0.0.0:8080
2025/09/15 05:53:26 Server is listening on 0.0.0.0:8080
2025/09/15 05:54:03 ERROR: Failed to deliver sampling response: no pending request found for session mcp-session-2ad06bc0-2dcd-408e-8c13-e9e07bf2d4d7, request 1
2025/09/15 05:54:03 ERROR: Failed to
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/51) · 2025-09-15 · closed · external user · 9 comments
### More load resources
Hi. I have a problem using the mcp server. I used the mcp-use client in python, the connection goes fine, however, when tools are found, a lot of resources appear that dramatically increase the context for transmission to the model, I looked for ways to disable but did not find. Can you tell me how to fix it?
```
2025-07-18 17:45:31,725 - mcp_use - DEBUG - Successfully connected to MCP implementation via SSE: http://localhost:8082/sse
2025-07-18 17:45:31,725 - mcp_use - DEBUG - Initializing MCP
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/26) · 2025-07-18 · closed · external user · 6 comments
### Web UI is not available on docker install
Running MCP in docker doesn't render a Web UI:
```
│ vmm-victoria-metrics-mcp-66bb85f877-6zzg2 time=2026-05-15T13:10:47.106Z level=INFO msg="Starting mcp-victoriametrics" version=1.19.0 date=2026-03-17T12:55:19Z mode=http addr=0.0.0.0:8080 │
│ vmm-victoria-metrics-mcp-66bb85f877-6zzg2 time=2026-05-15T13:10:53.702Z level=INFO msg="Starting server in HTTP mode" addr=0.0.0.0:8080 │
│ vmm-victoria-metrics-mcp-66bb85f877-6zzg2 time=2026-05-15T13:10:5
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/172) · 2026-05-15 · closed · external user · 3 comments
### Support dynamically selecting a host per tool call
We have multiple victoria metrics hosts, it would be nice if only a single MCP is needed in order to send tool calls off to a different host. Could be done as optional parameters on the tool call itself, or since in our case we use streamable-http a header would suffice
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/136) · 2026-03-12 · open · external user · 3 comments
### Can We Have Accessible Helm Chart (e.g. github pages)
I saw the helm chart was there in `k8s/helm` but I wonder, maybe we can have it accessible through Github Pages?
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/102) · 2025-12-05 · closed · external user · 3 comments
### Running container as non-root user
**Summary**
The current Docker image runs as root. This is not a best practice to run container in Kubernetes. Please update the Dockerfile to add and run as a dedicated non-root user instead of root.
**Risks of running as root**
Privilege escalation if the container is broken out of.
File permission surprises when shared volumes are used.
Incompatible with restrictive clusters (PSa/PSP, OPA/Gatekeeper, PodSecurity “restricted” profile).
**Proposal**
Update the Dockerfile to create a non-r
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/58) · 2025-09-17 · closed · external user · 3 comments
## Most recent
### The `documentation` tool is too attractive for agents
Whenever I have the MCP server enabled and ask agents questions completely unrelated to VictoriaMetrics, they try to use the `documentation` tool. For example here I asked Opus 4.8 a question about Backrest:
What do you think about renaming this tool to contain VictoriaMetrics in its name?
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/186) · 2026-06-16 · open · external user · 0 comments
### Alerts tool panics when limit is greater than returned alerts count
The `alerts` tool panics when it is called with a `limit` value greater than the number of alerts returned by the VictoriaMetrics API.
Request:
```json
{
"state": "firing",
"limit": 50
}
```
In my MCP client this tool is exposed as:
```text
mcp_mcp_victoriametrics_alerts
```
Error:
```text
2026-05-19 13:53:02,818 ERROR [20260519_135155_2a8e0a] tools.mcp_tool: MCP tool mcp-victoriametrics/alerts call failed: panic recovered in alerts tool handler: runtime error: slice bounds out of rang
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/175) · 2026-05-19 · open · external user · 0 comments
### can not send query request to vmgateway if it enable auth
Reproduce
Having VM cluster with vmgateway enable JWT token auth. Within this, the request don't need /prometheus prefix to be pass to vmgateway. However the mcp still sending request with prefix. So vmgateway repsone with 404
I tried to make a patch for fix this by removing the prefix, then the MCP works
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/130) · 2026-03-07 · open · external user · 0 comments
### The default tenant parameter for queries is 0, modify it to set the tenant parameter via environment variable
The default tenant parameter for queries in cluster mode is hardcoded to '0', which causes queries to fail when the actual tenant ID is different. Need to modify the code to allow setting the default tenant via an environment variable (e.g., VM_DEFAULT_TENANT) to support different tenant configurations.
https://xxxx.com/select/0/prometheus/api/v1/
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/113) · 2026-01-06 · closed · external user · 2 comments
### Installation Error Using Smithery
I'm receiving the following error when trying to install the mcp server using smithery.
`npx -y @smithery/cli install @VictoriaMetrics-Community/mcp-victoriametrics --client vscode`
✖ Failed to install @VictoriaMetrics-Community/mcp-victoriametrics
Error: API error occurred: {"error":"Server not found","request$":{},"response$":{},"body$":"{\"error\":\"Server not found\"}"}
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/109) · 2025-12-18 · closed · external user · 1 comment
### Implement detailed logging
Implement the ability to enable logging of requests and errors in HTTP/SSE modes
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/86) · 2025-10-30 · closed · 1 comment
### Error adding server to MCP Context Forge
Hi team,
I experience issues trying to add this MCP server to my IBM Context Forge app. I've deployed my Context Forge app and this server in the same Kubernetes cluster and the same namespace. The versions are the latest for each product.
I launch the server with the following config :
- VM_INSTANCE_ENTRYPOINT = http://\
- VM_INSTANCE_TYPE = cluster
- MCP_SERVER_MODE = http
- MCP_LISTEN_ADDR = 0.0.0.0:8080
I should be able to add this server by targeting the url **http://
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/78) · 2025-10-22 · closed · external user · 2 comments
### Hi team I get a strange regex error when using Gemini CLI as client
Hi team I get the error as above when I use Gemini CLI.
This error seems to be not happen when I attach it to Github Copilot though
[Read the thread](https://github.com/VictoriaMetrics/mcp-victoriametrics/issues/74) · 2025-10-13 · closed · external user · 2 comments
### Alert tool does not work with local models
When using the alerts tool with both qwen3:14b and gpt-oss:20b and witsy as the client I receive a chain of errors like the following, then the prompt either returns there are no alerts or that it was not able to read the response from the tool call, but using the same prompt with an anthropic model the response is parsed correctly and the output is returned to the user.