Renamed to mcp-server-linkedin. This transitional package forwards to it.
Nothing to run from here
Rag 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.
93/100
trust score
7
downloads a day
local
runs on your machine
92
downloads in 30d
What it does
Scoped hybrid search (BM25, embeddings, reranking) and grounded answers over local files and folders
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user masihmoafi-rag-mcp '--' uvx ragmcp-cli mcp
# 2 — ask your agent for something these tools do
# get_rag_settings, get_rag_capabilities, get_rag_models and 13 more
Rag costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MAAll 1 server
masihmoafi1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Rag 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 uv (docs.astral.sh/uv): uvx 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 masihmoafi-rag-mcp '--' uvx ragmcp-cli mcpReconnect, 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 — some of its tools take a key of its publisher’s own, and the rest work without.
What it asks of you
Nothing is required, but it can take OPENROUTER_API_KEY (OpenRouter key for answer synthesis and hosted reranking; exact-word search works without it) if you want to set it. Its publisher says some of its tools need it, and the rest work without.
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
16 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Show the RAG answer pipeline: embedding model, candidate and final passage counts, reranker, answer model, contextual retrieval, and detected runtimes or provider keys.
No parameter schema on file.
Show configured engine stages, providers, models, and credential readiness without making provider requests or exposing keys.
No parameter schema on file.
On demand, list configured and locally installed or cached model IDs. Does not query hosted catalogs, download or load models, or expose keys or cache paths.
No parameter schema on file.
Read the versioned evaluation question set in a shared RAG workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
Replace a shared workspace evaluation question set using its current revision. Rejects stale edits.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| revision | string/null | yes | — |
| questions | array | yes | — |
Run a shared workspace question set sequentially through engine retrieval and save a durable batch. Uses configured embedding/reranking providers; no answer synthesis. Passage counts are not correctness judgments.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| source_ids | array | no | — |
| question_revision | string | no | — |
| workspace_revision | string | no | — |
List saved evaluation batches, or read one batch by ID. Includes question snapshots and per-question trace IDs, without private passages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| batch_id | string | no | — |
| limit | integer | no | — |
| offset | integer | no | — |
Read human relevance judgments for one saved evaluation batch. Passage text is not included.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| batch_id | string | yes | — |
Score one saved evaluation batch (hit rate, recall, MRR, nDCG, precision) against passages marked relevant in any batch over the same sources.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| batch_id | string | yes | — |
Read answer checks for one saved evaluation batch: each answer, its claims marked supported or not by the saved passages, faithfulness and relevance. Checks are run from Studio or the CLI because they use paid model calls.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| batch_id | string | yes | — |
Mark one retained passage relevant or irrelevant, or clear its judgment. Requires the latest label revision.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| batch_id | string | yes | — |
| revision | string/null | yes | — |
| run_id | string | yes | — |
| rank | integer | yes | — |
| label | string/null | yes | — |
List shared workspace conversations, or read one private conversation including its saved answers and evidence.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| conversation_id | string | no | — |
| limit | integer | no | — |
| offset | integer | no | — |
Append a saved successful answer run to a shared workspace conversation using its current revision.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| conversation_id | string | yes | — |
| revision | string/null | yes | — |
| run_id | string | yes | — |
| question | string | yes | — |
Preview next-build boundaries or inspect published index metadata for one saved workspace source. Published metadata may be stale and is not a vector-table verification. Private chunk text and headings are omitted unless include_content is true; full source text is never returned. Chunk text is…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| source_id | string | yes | — |
| revision | string | no | — |
| view | string | no | — |
| scope_source_ids | array | no | Exact source selection used by the published index. |
| limit | integer | no | — |
| offset | integer | no | — |
| include_content | boolean | no | Explicitly return private text for this page of chunks. |
List shared local workspace IDs, or provide workspace_id to read its revision and source IDs, 100 sources per page (pass offset=next_offset for more). Returns metadata only, without source text, stored paths, or hashes. It does not search content; to find something in files, use…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | no | — |
| limit | integer | no | Sources per page, 100 by default |
| offset | integer | no | First source to return; use next_offset for the next page |
Import one explicit local file or bounded folder into a shared workspace. Requires its current revision (null to create); stale edits are rejected. Extracts text locally without indexing or model calls. Returns metadata and source IDs, never document text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | yes | — |
| path | string | yes | — |
| revision | string/null | yes | — |
| extensions | array | no | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- 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 Rag 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 93 / 100
Release 0.3.1 · scanned 12 Nov 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 score93
Findings7 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest880b96944e2fb53b8b4f59b772590f9f67e9fa25ad9939ec2ce19942e716df9c
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can start a fixed program (a process-spawning capability, not arbitrary code execution)
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 digest880b96944e2fb53b
Scanned2026-11-12
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 0.3.1. Pin a release below and the command asks for exactly that one.
0.3.1
12 Nov 2026
latestNo release note was published with this version.
0.3.0
11 Nov 2026
No release note was published with this version.
0.2.1
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 Rag 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.