Model Context Protocol server for Rollbar
Nothing to run from here
Backend Investigator is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
95/100
trust score
15
downloads a day
local
runs on your machine
770
downloads in 30d
What it does
Read-only Loki logs and PostgreSQL diagnostics for backend investigations in your AI client.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user backend-investigator-mcp '--' npx -y @mr.zedov/backend-investigator
# 2 — ask your agent for something these tools do
# list_projects, get_project_capabilities, investigate_backend and 11 more
Backend Investigator costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Backend Investigator as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user backend-investigator-mcp '--' npx -y @mr.zedov/backend-investigatorReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take BACKEND_INVESTIGATOR_WORKSPACE (Optional absolute Linux/WSL application root initialized with setup. Restricts tools and history to its bound project. Omit only for intentional shared mode.) if you want to set it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
14 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source is public; its licence metadata reads SEE LICENSE IN Backend Investigator Free Use License.txt rather than naming a licence
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Backend Investigator or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 95 / 100
Release 1.7.1 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score95
Findings2 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationnone
Surface digestcdd49eaf8a64b3daae6c5cc47a82b2f9ec298ad0eebebf7d1c1d5fbc3450adaf
Score vectorthreat 100 → client 95
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
14 of the 14 recovered tools are registered only when !Number.isSafeInteger(maximumBytes) || maximumBytes < 1024 || maximumBytes > 1e6 is false (dist/backend-investigator.mjs:7943) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
No tool is registered unconditionally · 14 only when !Number.isSafeInteger(maximumBytes) || maximumBytes < 1024 || maximumBytes > 1e6 is false (dist/backend-investigator.mjs:7943) — typically when a key or option is configured. All 14 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_projects conditional | no tags | |
| get_project_capabilities conditional | no tags | |
| investigate_backend conditional | no tags | |
| investigate_operation conditional | no tags | |
| investigate_deployment_regression conditional | no tags | |
| list_investigations conditional | no tags | |
| get_investigation conditional | no tags | |
| get_latest_deployment conditional | no tags | |
| inspect_service conditional | no tags | |
| inspect_database conditional | no tags | |
| inspect_metrics conditional | no tags | |
| inspect_redis conditional | no tags | |
| inspect_queue conditional | no tags | |
| search_logs conditional | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestcdd49eaf8a64b3da
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.7.1. Pin a release below and the command asks for exactly that one.
1.7.1
13 Oct 2026
latest- Improved investigation accuracy and safer conclusions: Redis slow commands now use their actual event time, preventing old events from being linked to current incidents. Findings distinguish shared request/trace/job IDs, verified dependencies, timing overlaps, and diagnostic hints. Hypotheses use more cautious confidence ratings when evidence is incomplete, sampled, or contradictory. Existing investigation history remains compatible.
1.7.0
12 Oct 2026
- Prometheus historical metrics through inspect_metrics, setup and CLI: scoped availability, HTTP latency/error/throughput, process resources and bounded before/after window comparison. Opt-in PostgreSQL performance statistics for statements, tables, indexes, VACUUM and I/O; existing health/activity/locks remain the default. Safe local MCP lifecycle diagnostics on stderr, without credentials, arguments or tool results. Workspace setup prints a Linux Node/npx @latest launch configuration. Package resolution happens on new starts, not while an MCP process is running. There are 14 MCP tools. Diagnostics remain read-only; no arbitrary SQL/PromQL or maintenance commands are exposed. Usage statistics retain their separate, explicit opt-in consent.
1.6.2
7 Oct 2026
No release note was published with this version.
1.5.0
6 Oct 2026
No release note was published with this version.
1.3.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Backend Investigator can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.