Name: Purple8 — AI-Native Application Backend
Author: purple8

Purple8 — AI-Native Application Backend MCP

Complete backend for AI-built apps: data, auth, workflows, SLAs, HITL & RAG in 176 MCP tools.

Tool-list grade A Remote · Streamable HTTP API key 28 tools v0.72.1

No reviews yet by purple8 The publisher’s own endpoint — this marketplace is not in the path

96/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Complete backend for AI-built apps: data, auth, workflows, SLAs, HITL & RAG in 176 MCP tools.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http purple8-ai-native-application-backend-mcp 'https://purple8-graph-sandbox.fly.dev/mcp?profile=starter' --header 'X-API-Key: ${X_API_KEY}'

# 2 — ask your agent for something these tools do
#   rag.query, rag.hybrid_query, rag.profile_collection and 25 more

It needs X_API_KEY (Purple8 API key or free 30-day Cloud Sandbox key from https://www.purple8.ai/try/graph/): this sends it in the X-API-Key header from your environment, so export it first — its endpoint answers 401 without it.

Purple8 — AI-Native Application Backend costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

purple82 servers

2 categories

All 2 servers

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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.

Claude Codedeclared by this listing

This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads X_API_KEY (Purple8 API key or free 30-day Cloud Sandbox key from https://www.purple8.ai/try/graph/) from your environment each time it connects and sends it in the X-API-Key header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx X_API_KEY … and open a new terminal (Windows).

claude mcp add --scope user --transport http purple8-ai-native-application-backend-mcp 'https://purple8-graph-sandbox.fly.dev/mcp?profile=starter' --header 'X-API-Key: ${X_API_KEY}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: X-API-Key header — Purple8 API key or free 30-day Cloud Sandbox key from https://www.purple8.ai/try/graph/. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.

What you approve

28 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.

Only tools that write or reach the network

Flat Vector RAG — retrieves the most relevant graph nodes by pure vector similarity (HNSW + RRF fusion + keyword fallback), then calls the configured LLM to generate a grounded answer. Fastest of the three RAG modes (p50 ~45 ms, MRR 0.64); best for single-hop factual questions. Use rag.graph_query or rag.hybrid_query for multi-hop or relationship-heavy questions.

Parameter	Type	Required	Notes
question	string	yes	The question to answer.

Hybrid Graph-Vector RAG — fuses vector similarity AND graph structural signals at every stage: dual-seed fusion (Weighted RRF over vector rank + degree centrality), vector-guided BFS, and semantic path scoring. Highest accuracy: MRR 0.85, multi-hop 0.91. ~5x slower (p50 ~240 ms). Recommended as the default RAG tool for agents that need high quality.

Parameter	Type	Required	Notes
question	string	yes	The question to answer.
mode	string	no	Fusion mode. 'balanced' for most questions; 'graph_first' for dense-relationship queries; 'vector_first' for semantic similarity.
fusion_alpha	number	no	Explicit graph weight (0.0=pure vector, 1.0=pure graph). Overrides mode.
max_hops	integer	no	BFS expansion depth (1-5). Default 2.
seed_k	integer	no	Seed nodes per signal (1-20). Default 5.
max_nodes	integer	no	Maximum subgraph nodes in context (5-200). Default 50.
write_inferred	boolean	no	Persist LLM-inferred edges back to the graph. Default false.
vector_expansion	boolean	no	Filter BFS neighbours by cosine similarity. Default true.
semantic_path_scoring	boolean	no	Rank paths by keyword overlap + edge-type bonuses. Default true.
label_filter	array	no	Restrict retrieval to nodes with these labels.
max_tokens	integer	no	LLM output token budget. Default 1024.
temperature	number	no	LLM sampling temperature. Default 0.0.
collection_profile	string	no	Name of a saved CollectionProfile (from rag.tune_collection save_as). Fills in mode/fusion_alpha/max_hops/seed_k as defaults — explicit params always win.

Analyse the graph topology and return recommended RAG retrieval settings. Profiles node count, edge density, degree distribution, edge-type distribution, and embedding coverage, then derives concrete values for fusion_alpha, max_hops, seed_k, vector_weight, k, and mode. Call this before tuning rag.hybrid_query on a new corpus or collection. Returns topology_class (sparse/moderate/dense), a 'rec

Parameter	Type	Required	Notes
label_filter	array	no	Restrict analysis to nodes with these labels. Omit for whole graph.

Execute a Cypher query against the Purple8 knowledge graph and return matching records. Use for nodes, edges, paths, or aggregated data.

Parameter	Type	Required	Notes
cypher	string	yes	The Cypher query to execute.
parameters	object	no	Optional named parameters.

Find the k nearest nodes to a natural-language query using the HNSW vector index.

Parameter	Type	Required	Notes
query_text	string	yes	The search query in natural language.
label	string	no	Restrict search to nodes with this label.
k	integer	no	Number of results to return. Default 5.

Combine vector similarity with graph traversal for highest-recall retrieval. Best when graph structure matters.

Parameter	Type	Required	Notes
query_text	string	yes	The search query in natural language.
label	string	no	Restrict search to nodes with this label.
k	integer	no	Number of results to return. Default 10.

Walk the graph from a starting node following edges up to a given depth.

Parameter	Type	Required	Notes
node_id	string	yes	ID of the starting node.
depth	integer	no	Maximum traversal depth. Default 2.
edge_type	string	no	Restrict to edges of this type. Omit for all types.
direction	string	no	Edge direction. Default 'both'.

Insert a new node into the graph (accepts type, label, or node_type). Requires editor role.

Parameter	Type	Required	Notes
node_id	string	yes	Unique identifier for the node.
type	string	no	Node label / type (e.g. 'Person', 'Company').
label	string	no	Alias for type (e.g. 'Document', 'Borrower').
node_type	string	no	Alias for type.
labels	array	no	Optional additional labels.
properties	object	no	Key-value properties.

Create a directed edge (relationship) between two existing nodes. This is the primary agentic handoff mechanism — agents write their output as edges (e.g. DERIVED_FROM, RISK_ASSESSMENT, EXTRACTED_FROM) so downstream agents can discover work by querying graph state rather than passing messages. edge_id is auto-generated (UUID4) when omitted. Requires editor role.

Parameter	Type	Required	Notes
source_id	string	yes	ID of the source (tail) node.
target_id	string	yes	ID of the target (head) node.
edge_type	string	yes	Relationship type label (e.g. 'DERIVED_FROM', 'RISK_ASSESSMENT', 'EXTRACTED_FROM').
edge_id	string	no	Unique identifier for the edge. Auto-generated UUID4 when omitted.
properties	object	no	Key-value edge properties (e.g. {"confidence": 0.9, "assessor": "legal"}).
weight	number	no	Edge weight for traversal algorithms. Default 1.0.

Update properties or labels on an existing node. Properties are merged with existing values (patch semantics — only the keys you supply are changed). Labels replace the full label set when provided. Use this to advance agent relay state, e.g. setting {"status": "enriched", "handoff_to": null} to hand off work to the next agent in a relay pipeline. Requires editor role.

Parameter	Type	Required	Notes
node_id	string	yes	ID of the node to update.
properties	object	no	Properties to merge into the node (patch semantics).
labels	array	no	Replacement label set (replaces all existing labels when provided).

Retrieve a node and all its stored properties by ID.

Parameter	Type	Required	Notes
node_id	string	yes	ID of the node to retrieve.

Extract entities and relationships from raw text and write them into the graph. Calls preview first, then commits the complete extraction on success. auto_commit=false returns a review-only preview. Pending jobs return job_id for resumption. Original bytes are not stored automatically; supply file_ref or use data.commit with file_bytes_b64 if needed. After an interrupted write, ask the user to con

Parameter	Type	Required	Notes
text	string	yes	The raw text to extract knowledge from.
source_name	string	yes	Label for the source document (provenance).
profile_hint	string	no	Extraction profile; omit for auto-detection.
auto_commit	boolean	no	false returns the complete preview without graph writes. Review then use data.commit.
job_id	string	no	Resume an earlier extraction instead of submitting again; repeat the original input arguments.
wait_seconds	integer	no	Maximum wait for an admitted extraction. Pending jobs are NOT committed; resume with job_id.
file_ref	string	no	Optional existing Graph file_id in this tenant, used as the original/document anchor at commit.

Commit a reviewed extraction or your own extractor's output without invoking DocIntel. Uses the complete POST /ingest/commit contract: entities, relationships, Markdown, spans, tables/pages, context, file_ref or inline file_bytes_b64 and ingestion options. Existing entities are linked, not edited, unless update_entities=true. For extractor-generated IDs use identity_policy='review_conflicts': name

Parameter	Type	Required	Notes
entities	array	yes	—
relationships	array	yes	—
identity_policy	string	no	review_conflicts rejects conflicting names/types/identifiers and cross-document name-only matches before writes. Supply matching stable identifiers, same-source provenance, or explicit link_existing c
source_name		no	—
metadata	object	no	Preserve extraction metadata. For a stored File, sha256 binds the review to original bytes (not Markdown); optional file_version pins its positive integer version. A changed/missing bound source retur
doc_type		no	—
chunking_hint		no	—
section_boundaries	array	no	—
suggested_embedding_model		no	—
markdown	string	no	—
markdown_sections	array	no	—
tables	array	no	—
pages	array	no	—
links	array	no	—
file_ref		no	—
file_bytes_b64		no	—
context		no	—
session_id		no	—
build_similarity_edges	boolean	no	Build SIMILAR_TO edges to cross-batch neighbours via vector search. On by default — turns every commit into a native hybrid ingest.
similarity_threshold	number	no	Minimum cosine similarity for SIMILAR_TO edge creation.

Create a new Journey Engine instance for an entity and move it to the first stage. All transitions are recorded as immutable graph edges. Requires editor role.

Parameter	Type	Required	Notes
journey_type	string	yes	Journey type to instantiate (e.g. 'sales-cycle').
entity_id	string	yes	ID of the entity node the journey is for.

Advance a journey instance to the next stage. Actor and notes are written to the audit trail as an ADVANCED_TO edge. Requires editor role.

Parameter	Type	Required	Notes
instance_id	string	yes	ID of the journey instance.
to_stage	string	yes	Stage name to advance to.
notes	string	no	Optional notes for the audit trail.

Return the full state and audit trail for a journey instance — every stage transition, AI recommendation, and HITL decision.

Parameter	Type	Required	Notes
instance_id	string	yes	ID of the journey instance.

Define a new journey type (workflow template) with ordered stages, owner systems, and per-stage SLA policies. Once defined, instances can be started with journey.start. Call this first when building any new workflow — the agent can define the entire process in one call. Use overwrite=true to update an existing definition. Requires journey:admin permission (admin or super_admin by default). Use

Parameter	Type	Required	Notes
operation	string	no	—
ai_enabled	boolean	no	Required for configure_ai. Explicit opt-in to automatic LLM calls for this tenant.
journey_type	string	no	Unique snake_case name for this workflow (e.g. 'loan_application', 'supplier_approval').
description	string	no	Human-readable description of what this journey tracks.
stages	array	no	Ordered list of stages. First stage is the initial state.
overwrite	boolean	no	Replace an existing definition with the same journey_type. Default false.

List journey instances with optional filters. Use this to discover what is in flight, find instances for a specific entity, or check all instances of a given type. Also returns all defined journey types when called with no arguments. Essential for any agent monitoring or orchestrating workflows. Set runtime_status=true to inspect this tenant's advisor enablement, provider readiness and delivery

Parameter	Type	Required	Notes
journey_type	string	no	Filter by journey type (e.g. 'loan_application').
entity_id	string	no	Filter by the entity the journey is tracking.
status	string	no	Filter by instance status.
list_types	boolean	no	Return defined journey type names instead of instances. Default false.
runtime_status	boolean	no	Return tenant Journey AI configuration/readiness instead of instances.

List pending Human-In-The-Loop (HITL) tasks — decisions that require a human (or agent acting as human proxy) to approve, reject, or escalate before the journey can continue. Returns task ID, title, assigned role, description, and the stage the journey is waiting on. An agent can use this to surface pending decisions to the user or take autonomous action if authorised.

Parameter	Type	Required	Notes
instance_id	string	no	Restrict to HITL tasks for a specific journey instance.
assigned_role	string	no	Filter by role (e.g. 'compliance_officer').
status	string	no	Filter by task status. Default: pending.

Resolve a Human-In-The-Loop (HITL) task — approve, reject, or escalate it. On approval the journey automatically advances to the next stage if advance_to_stage is set. The decision is written to the immutable graph audit trail with the actor and timestamp. An AI agent acting as a human proxy must set actor to the user or role it is acting on behalf of. Requires editor role.

Parameter	Type	Required	Notes
task_id	string	yes	ID of the HITL task to resolve.
action	string	yes	Resolution action.
actor	string	yes	User or system making the decision (written to audit trail).
decision	string	no	Decision label for complete actions (e.g. 'approved', 'denied'). Default 'approved'.
advance_to_stage	string	no	Stage to advance the journey to on completion. Omit to leave stage unchanged.
notes	string	no	Notes written to the audit trail.
new_assigned_role	string	no	New role to escalate to (required when action=escalate).

Send a document file (PDF, DOCX, PPTX, XLSX, HTML, IFC, CSV, …) to Purple8 DocIntel for parsing, entity extraction, and graph ingestion. The document is fetched by DocIntel from a public URL, not a local path. The complete extraction is committed only when finished successfully. auto_commit=false returns a review-only preview; pending jobs return job_id for resumption. URL extraction does not ret

Parameter	Type	Required	Notes
url	string	yes	Publicly accessible URL of the document to fetch and process.
source_name	string	yes	Label for provenance tracking (e.g. 'loan_policy_v3.pdf').
profile_hint	string	no	Extraction profile; omit for auto-detection.
auto_commit	boolean	no	false returns the complete preview without graph writes. Review then use data.commit.
job_id	string	no	Resume an earlier extraction instead of submitting again; repeat the original input arguments.
wait_seconds	integer	no	Maximum wait for an admitted extraction. Pending jobs are NOT committed; resume with job_id.
file_ref	string	no	Optional existing Graph file_id in this tenant, used as the original/document anchor at commit.

Idempotently assert one native RDF quad with exact lexical terms, explicit blank-node scope and optional graph name. Uses existing node/edge create and read permissions, record policies and API-key label restrictions. No bulk import or caller-supplied metadata.

Parameter	Type	Required	Notes
statement		yes	—

Read-only indexed RDF/LPG pattern query with policy-filtered evidence. Use tagged rdf, lpg and lpg_edge patterns. Returns unified bindings and evidence or, with output_format=nquads, a JSON envelope containing selected asserted N-Quads and selection metadata. Raw work stats are withheld (stats=null). No inferred RDF, writes, import, or whole-corpus export. Existing read permissions apply; N-Quads

Parameter	Type	Required	Notes
patterns	array	yes	—
bindings		no	—
node_bindings		no	—
limit	integer	no	—
limits		no	—
max_output_bytes	integer	no	—
output_format	string	no	—

Return the total number of nodes in the graph, optionally filtered by label. A cheap situational-awareness call an agent can make before deciding how to query or ingest.

Parameter	Type	Required	Notes
label	string	no	Count only nodes with this label. Omit for all nodes.

List every node type (label) in the graph with how many nodes carry it, largest first. Cheap — O(types), not O(nodes). Call this first to learn what the graph contains (e.g. Person, Account, Invoice) before querying or filtering by label.

No parameter schema on file.

Validate the tenant's live graph data against the defined schema. Reports missing required properties, type/enum violations, edge source/target-type violations, and orphan labels (labels present in the graph but undefined in the schema). Returns valid=true with empty violation lists when the graph conforms.

No parameter schema on file.

Define a new node type — the primitive that lets an agent build the data model itself. The type_name becomes the canonical label for nodes of this type. Set app_id to make the type a per-app IAM boundary (only matching API keys may touch its nodes). Declare properties with per-field type / required / enum constraints, and immutable_properties that cannot change after creation. Fails 409 if the

Parameter	Type	Required	Notes
type_name	string	yes	Canonical node label (1–100 chars).
description	string	no	Human-readable description of the type.
app_id	string	no	Owning application ID — makes this type an app-level IAM boundary. Omit for tenant-wide types.
data_classification	string	no	public \| internal \| restricted \| highly_restricted. Default internal.
properties	object	no	Map of property name → definition. Each definition may set: type (string\|str\|integer\|int\|float\|number\|boolean\|bool\|datetime\|list\|array\|dict\|object), required (bool), description, enum (list of allowe
required_labels	array	no	Additional labels every node of this type must carry.
immutable_properties	array	no	Properties that cannot be modified after node creation.
allowed_edge_types	array	no	Outgoing edge types this node type may participate in. Omit for unrestricted.

Define a new edge (relationship) type. Constrain which node types may be the source/target, declare edge properties, and set cardinality (one_to_one | one_to_many | many_to_one | many_to_many). Fails 409 if the type already exists.

Parameter	Type	Required	Notes
type_name	string	yes	Canonical edge type name (1–100 chars).
description	string	no	—
app_id	string	no	—
source_node_types	array	no	Allowed source node types. Omit for any.
target_node_types	array	no	Allowed target node types. Omit for any.
properties	object	no	Map of property name → definition. Each definition may set: type (string\|str\|integer\|int\|float\|number\|boolean\|bool\|datetime\|list\|array\|dict\|object), required (bool), description, enum (list of allowe
cardinality	string	no	one_to_one \| one_to_many \| many_to_one \| many_to_many. Default many_to_many.
data_classification	string	no	public \| internal \| restricted \| highly_restricted. Default internal.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Purple8 — AI-Native Application Backend or to call it, at any volume.

ATool-list grade · score 96 / 100

Release 0.72.1 · scanned 7 Nov 2026

Graded from the tools this server lists, not from its source code.

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 score96

Findings0 threat · 0 capability

Capabilityminimal

Coveragemanifest

Verificationnot in this report

Surface digest81f461880a5046575a5b744aa01c69c5b9108c672a0f80c66330cb417142fd88

Score vectorthreat 100 → client 96

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

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.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

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. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
rag.query	no tags
rag.hybrid_query	no tags
rag.profile_collection	no tags
graph.query	no tags
graph.vector_search	no tags
graph.hybrid_search	no tags
graph.traverse	no tags
graph.add_node	no tags
graph.add_edge	no tags
graph.update_node	no tags
graph.get_node	no tags
data.ingest_text	no tags
data.commit	no tags
journey.start	no tags
journey.advance	no tags
journey.status	no tags
journey.define	no tags
journey.list	no tags
journey.list_hitl	no tags
journey.resolve_hitl	no tags
data.ingest_file	no tags
graph.assert_statement	no tags
graph.semantic_query	no tags
graph.counts	no tags
graph.labels	no tags
schema.validate	no tags
schema.define_node_type	no tags
schema.define_edge_type	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 digest81f461880a504657

Scanned2026-11-07

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.