A2A Governance Bridge MCP server. Tools: verify agent compliance, authorize a2a transaction, get trust registry. Built by MEOK AI Labs.
Free
Nothing to run from here
Neuronsearchlab 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.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
MCP server for NeuronSearchLab recommendations, search, catalogue, analytics, and platform operations.
Quickstart
# 1 — run it from where its publisher ships it
npx -y @neuronsearchlab/mcp
# 2 — the plan is chosen at checkout, in the browser
# 3 — ask your agent something
> MCP server for NeuronSearchLab recommendations, search, catalogue, analytics, and platform operations.
Publishernot claimed
NEAll 1 server
neuronsearchlab1 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 Neuronsearchlab 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. It is scanned, signed and pinned to the version you choose — 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. Claude Code registers it in one command.
claude mcp add neuronsearchlab-mcp -- npx -y @neuronsearchlab/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
This is a paid listing, so the CLI has to be signed in and the licence has to be on your account — how the login works. Until then the install stops with the price rather than half-writing a config entry.
What it asks of you
Nothing is required, but it can take NSL_CLIENT_ID, NSL_CLIENT_SECRET, NSL_PLATFORM_MODE, NSL_API_KEY if you want to set them.
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
73 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.
Fetch personalised recommendations for a user. Returns ranked items with scores.
Takes no parameters.
Example callreturns →
Fetch the next auto-generated recommendation section for a user.
Takes no parameters.
Example callreturns →
Record a user interaction event (click, view, purchase, etc.).
Takes no parameters.
Example callreturns →
Add or update an item in the recommendation catalogue.
Takes no parameters.
Example callreturns →
Partially update an existing item.
Takes no parameters.
Example callreturns →
Permanently remove one or more items from the recommendation catalogue.
Takes no parameters.
Example callreturns →
Search the recommendation catalogue by keyword.
Takes no parameters.
Example callreturns →
Explain why a specific item was (or would be) ranked at a particular position for a user.
Takes no parameters.
Example callreturns →
Get the authenticated team\
Takes no parameters.
Example callreturns →
List all recommendation contexts (feeds) configured for your team.
Takes no parameters.
Example callreturns →
Create a new recommendation context (feed).
Takes no parameters.
Example callreturns →
Update an existing recommendation context.
Takes no parameters.
Example callreturns →
Delete a recommendation context. This also removes associated pipelines and rules.
Takes no parameters.
Example callreturns →
List all ranking pipelines.
Takes no parameters.
Example callreturns →
Create a new ranking pipeline with default stages.
Takes no parameters.
Example callreturns →
Update an existing ranking pipeline.
Takes no parameters.
Example callreturns →
Delete a ranking pipeline.
Takes no parameters.
Example callreturns →
List ranking rules, optionally filtered by context.
Takes no parameters.
Example callreturns →
Create a new ranking rule. Rule types:
Takes no parameters.
Example callreturns →
Update an existing ranking rule.
Takes no parameters.
Example callreturns →
Delete a ranking rule.
Takes no parameters.
Example callreturns →
Enable or disable a ranking rule without deleting it.
Takes no parameters.
Example callreturns →
Get the full configuration of a specific recommendation context by ID.
Takes no parameters.
Example callreturns →
Get the full configuration of a specific ranking pipeline by ID.
Takes no parameters.
Example callreturns →
Activate a ranking pipeline so it begins serving ranked results.
Takes no parameters.
Example callreturns →
Deactivate a ranking pipeline so it stops serving results without being deleted.
Takes no parameters.
Example callreturns →
Duplicate an existing pipeline with all its stages and configuration. Useful for creating experiment variants or safe copies before making changes.
Takes no parameters.
Example callreturns →
Get the full configuration of a specific ranking rule by ID, including conditions and action.
Takes no parameters.
Example callreturns →
Enable a ranking rule that was previously disabled.
Takes no parameters.
Example callreturns →
Disable a ranking rule without deleting it. Useful for temporarily pausing rules during debugging or campaigns.
Takes no parameters.
Example callreturns →
Set the priority order of rules by providing rule IDs in the desired order. The first rule in the list gets the highest priority and is evaluated first.
Takes no parameters.
Example callreturns →
List all user segments. Segments group users by shared behaviours or attributes and can be referenced in rules and campaigns.
Takes no parameters.
Example callreturns →
Get the full definition of a specific user segment, including all its conditions.
Takes no parameters.
Example callreturns →
Create a new user segment with membership conditions.
Takes no parameters.
Example callreturns →
Update an existing user segment definition.
Takes no parameters.
Example callreturns →
Delete a user segment. Any rules referencing this segment will need to be updated.
Takes no parameters.
Example callreturns →
Get size and overlap statistics for a user segment — how many users match, percentage of total users, and overlap with other segments.
Takes no parameters.
Example callreturns →
List all A/B experiments with their current status (draft, running, paused, completed).
Takes no parameters.
Example callreturns →
Get the full configuration of a specific A/B experiment including variants, traffic splits, and current metrics.
Takes no parameters.
Example callreturns →
Create a new A/B experiment comparing pipeline variants.
Takes no parameters.
Example callreturns →
Update an experiment that is in draft status.
Takes no parameters.
Example callreturns →
Start an A/B experiment. Traffic will begin splitting between variants immediately. The experiment moves from draft to running status.
Takes no parameters.
Example callreturns →
Stop a running A/B experiment and mark it as completed. Results are preserved for analysis.
Takes no parameters.
Example callreturns →
Get the most recently calculated statistical results for a completed or running experiment without changing stored data.
Takes no parameters.
Example callreturns →
Recalculate experiment metrics from current recommendation and event data, store the refreshed metrics, and return the updated experiment results.
Takes no parameters.
Example callreturns →
List all campaigns — time-bounded rule injections that activate on a schedule (e.g. flash sales, seasonal promotions).
Takes no parameters.
Example callreturns →
Get the full configuration of a specific campaign including start/end dates and injected rules.
Takes no parameters.
Example callreturns →
Create a time-bounded campaign that injects ranking rules between a start and end datetime.
Takes no parameters.
Example callreturns →
Update a campaign — change its name, description, or start/end dates.
Takes no parameters.
Example callreturns →
Delete a campaign and its associated rules.
Takes no parameters.
Example callreturns →
Activate a paused campaign so it starts injecting rules again.
Takes no parameters.
Example callreturns →
Pause an active campaign, temporarily stopping its rule injections without deleting it.
Takes no parameters.
Example callreturns →
List recent model training jobs with their status (running, completed, failed). Training jobs re-train the ranking model on new interaction data.
Takes no parameters.
Example callreturns →
Get a customer-facing status summary for a specific training job without returning infrastructure identifiers or raw logs.
Takes no parameters.
Example callreturns →
Start a model training job from an existing template. This consumes training quota and may incur usage charges; auto-promotion options can replace the model serving live traffic.
Takes no parameters.
Example callreturns →
Cancel a running training job.
Takes no parameters.
Example callreturns →
Get ranking performance metrics for a pipeline or context: CTR by position, overall CTR, conversion rate, diversity score, catalogue coverage, and revenue per session.
Takes no parameters.
Example callreturns →
Get live metrics for a specific A/B experiment broken down by variant — CTR, conversion rate, revenue per session, and statistical significance.
Takes no parameters.
Example callreturns →
Get ranking performance metrics broken down by user segment — useful for understanding how different user groups respond to your ranking configuration.
Takes no parameters.
Example callreturns →
Get served counts, event breakdown, unique-item activity, and click-through rate for a specific user over a time window.
Takes no parameters.
Example callreturns →
Get served counts, event breakdown, watch/click counts, and click-through rate for a specific item over a time window.
Takes no parameters.
Example callreturns →
Compare two items head-to-head by served count, events, clicks, and click-through rate over the same time window.
Takes no parameters.
Example callreturns →
List the top items by served count or by matching event activity such as watch or click over a time window. For generic
Takes no parameters.
Example callreturns →
List all API keys for the team with their names, scopes, environments, and last-used timestamps.
Takes no parameters.
Example callreturns →
Create a new API key with specified permissions (scopes). The full key is returned once and cannot be retrieved again.
Takes no parameters.
Example callreturns →
Revoke an API key. This immediately invalidates the key and cannot be undone.
Takes no parameters.
Example callreturns →
List configured third-party integrations (webhooks, data connectors, export targets, etc.).
Takes no parameters.
Example callreturns →
List all configured event types (click, view, purchase, etc.) for the team.
Takes no parameters.
Example callreturns →
Create a new event type that can be tracked in the recommendation model.
Takes no parameters.
Example callreturns →
Update an existing event type\
Takes no parameters.
Example callreturns →
Permanently delete an event type. This cannot be undone.
Takes no parameters.
Example callreturns →
List the internal admin-console API routes that the standalone MCP can reach in internal mode.
Takes no parameters.
Example callreturns →
Fallback tool for internal mode only. Calls safe admin-console /api routes directly when no dedicated MCP tool exists.
Takes no parameters.
Example callreturns →
Standardmost installed
$19 / month
- 16,000 calls a month, included
- 192 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
Pro
$69 / month
- 160,000 calls a month, included
- 1,920 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
No call is billed on its own, and this plan carries no monthly call limit. $19 a month covers every tool 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: $8.42
$16.58 left
ATrust score 97 / 100
Release 1.0.0 · scanned 25 Aug 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 score97
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digestc2fa2acf8f947e1deeed6c98856ec61eed31e512d7823108cae9b70f3bbfe195
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 (73 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>".
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_recommendations | untrusted-input | |
| get_auto_recommendations | untrusted-input | |
| track_event | no tags | |
| upsert_item | no tags | |
| patch_item | no tags | |
| delete_items | no tags | |
| search_items | no tags | |
| explain_ranking | no tags | |
| get_account_plan | no tags | |
| list_contexts | no tags | |
| create_context | no tags | |
| update_context | no tags | |
| delete_context | no tags | |
| list_pipelines | no tags | |
| create_pipeline | no tags | |
| update_pipeline | no tags | |
| delete_pipeline | no tags | |
| list_rules | no tags | |
| create_rule | no tags | |
| update_rule | no tags | |
| delete_rule | no tags | |
| toggle_rule | no tags | |
| get_context | no tags | |
| get_pipeline | no tags | |
| activate_pipeline | no tags | |
| deactivate_pipeline | no tags | |
| clone_pipeline | no tags | |
| get_rule | no tags | |
| enable_rule | no tags | |
| disable_rule | no tags | |
| reorder_rules | no tags | |
| list_segments | no tags | |
| get_segment | no tags | |
| create_segment | no tags | |
| update_segment | no tags | |
| delete_segment | no tags | |
| get_segment_stats | no tags | |
| list_experiments | no tags | |
| get_experiment | no tags | |
| create_experiment | no tags | |
| update_experiment | no tags | |
| start_experiment | no tags | |
| stop_experiment | no tags | |
| get_experiment_results | no tags | |
| refresh_experiment_results | no tags | |
| list_campaigns | no tags | |
| get_campaign | no tags | |
| create_campaign | no tags | |
| update_campaign | no tags | |
| delete_campaign | no tags | |
| activate_campaign | no tags | |
| pause_campaign | no tags | |
| list_training_jobs | no tags | |
| get_training_job | no tags | |
| create_training_job | no tags | |
| cancel_training_job | no tags | |
| get_ranking_metrics | no tags | |
| get_experiment_metrics | no tags | |
| get_segment_metrics | no tags | |
| get_user_analytics | no tags | |
| get_item_analytics | no tags | |
| compare_items | no tags | |
| top_items | no tags | |
| list_api_keys | no tags | |
| create_api_key | no tags | |
| revoke_api_key | no tags | |
| list_integrations | no tags | |
| list_event_types | no tags | |
| create_event_type | no tags | |
| update_event_type | no tags | |
| delete_event_type | no tags | |
| list_platform_routes | no tags | |
| call_platform_api | 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 digestc2fa2acf8f947e1d
Scanned2026-08-25
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
Pinned to 1.0.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
1.0.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Neuronsearchlab in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
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 an account with 50 real tool calls against it.