Lithtrix MCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Lithtrix identity, shared memory and trust tools: Do self-registration and metered browsing keep reputation confidence distinct from verified identity claims?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Persistent identity, memory, trust/reputation and delegated swarm primitives for AI agents.

What we know

Agent infrastructure MCP for Lithtrix MIRC (Memory, Identity, Reputation, Commons) plus trust, directory, keys and swarm/delegation features. Agents self-register and use a persistent Lithtrix identity across providers/frameworks.

Maintenance / activity evidence

lithtrix-mcp 0.20.9 published 2026-10-05T05:56:18.213Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Identity/memory/reputation plus delegation and trace-writing authority. Writes: Register identity; Write memory/commons/traces; Spawn/delegate child agents; Potential key/reputation actions.
Persistent agent credential.
Sensitive access: Persistent agent identity, Memory contents, Delegation credentials

Identity and delegation primitives can expand agent authority; protect keys and review delegated scope.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do self-registration and metered browsing keep reputation confidence distinct from verified identity claims?

The bounded review of the publisher's documented Lithtrix identity, shared memory and trust tools and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Identity and delegation primitives can expand agent authority; protect keys and review delegated scope.
Identity/memory/reputation plus delegation and trace-writing authority.
Persistent agent credential.
Memory/identity/trust state is stored by Lithtrix; some local client-side signing is used for delegation.
Reviewed write actions: Register identity; Write memory/commons/traces; Spawn/delegate child agents; Potential key/reputation actions
Sensitive access: Persistent agent identity, Memory contents, Delegation credentials
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
full memory retention/privacy
exact current paid-tool pricing
Some browse/search operations are metered.
Swarm/delegation features create real identity/authority state.
Exact privacy/retention for stored memory was not fully established here.

Original activity observations

lithtrix-mcp 0.20.9 published 2026-10-05T05:56:18.213Z

Technical identity

npm/lithtrix-mcp

Exact implementation source: https://www.npmjs.com/package/lithtrix-mcp ↗
Reviewed resource type: Framework
Repository identity: lithtrix/lithtrix-mcp
Package identity: npm:lithtrix-mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry metadata ↗
lithtrix-mcp
Recorded package identity, distribution or download evidence.
Evidence source ↗
lithtrix.ai/
Source material retained for this review.
Includes references whose attribution is not established.
Directory reference ↗
glama.ai/mcp/servers/lithtrix/lithtrix-mcp/tree
Source material retained for this review.
Includes references whose attribution is not established.

Setup · Watchlist

Framework setup

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install framework / integration
Publisher instructions
Publisher-documented package/connection route; replace placeholders and verify host-specific syntax.
Publisher setup example · Publisher instructions
npx -y lithtrix-mcp
Configure / authenticate
MCP100 setup guide
Register stdio launcher in MCP client; create/register agent as documented and set LITHTRIX_API_KEY for authenticated calls. Browse/search can cost credits.
Use correct transport and published host config. Never paste secrets in chat; server registration is separate from software installation.
Environment settings: LTX credential issued through self-registration or account flow
Check connection
Suggested check
Check tool discovery; use a free identity or read-only listing tool before any paid browse/search.
Remove / uninstall / revoke
MCP100 setup guide
If registered as `lithtrix-mcp` in Claude Code, remove its exact client entry with `claude mcp remove lithtrix-mcp`; for Cursor/Claude Desktop/Codex, remove the matching MCP entry in that host settings. This client removal is MCP100-composed, not a vendor uninstall instruction. Npx does not imply a global install; do not delete user data or revoke credentials implicitly. For an explicitly globally installed package (not npx-only), npm uninstall -g lithtrix-mcp.
Conditional host / package cleanup · Claude Code only · MCP100 composed guide
claude mcp remove lithtrix-mcp

Official Documentation & Sources

What it does

Agent infrastructure MCP for Lithtrix MIRC (Memory, Identity, Reputation, Commons) plus trust, directory, keys and swarm/delegation features. Agents self-register and use a persistent Lithtrix identity across providers/frameworks.

Capability: Files & Knowledge
Resource type: Framework
Best fit: Persistent identity, memory, trust/reputation and delegated swarm primitives for AI agents.

Representative uses

Create persistent agent identity/passport
Store/query memory and commons knowledge
Query trust/reputation/directory
Spawn/delegate child agents and maintain tamper-evident traces

Limitations

Some browse/search operations are metered.
Swarm/delegation features create real identity/authority state.
Exact privacy/retention for stored memory was not fully established here.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Persistent agent credential.
Permissions: Identity/memory/reputation plus delegation and trace-writing authority.
Data handling: Memory/identity/trust state is stored by Lithtrix; some local client-side signing is used for delegation.
Cost: freemium_metered
Risk and cautions: Identity and delegation primitives can expand agent authority; protect keys and review delegated scope.

Access scope and cautions

Write actions: Register identity Write memory/commons/traces Spawn/delegate child agents Potential key/reputation actions
Sensitive access: Persistent agent identity Memory contents Delegation credentials
Risk level: high

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Create persistent agent identity/passport; Store/query memory and commons knowledge; Query trust/reputation/directory; Spawn/delegate child agents and maintain tamper-evident traces.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y lithtrix-mcp. Recorded transport: stdio, remote. Recorded environment-variable notes: LTX credential issued through self-registration or account flow. No configuration values are supplied here. Prerequisites: MCP client. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Lithtrix agent key/passport; package docs describe self-registration and a common ltx_* credential.

Can it modify data or perform write operations?

Documented write actions include: Register identity; Write memory/commons/traces; Spawn/delegate child agents; Potential key/reputation actions. Recorded permission boundary: Identity/memory/reputation plus delegation and trace-writing authority.

What data-handling boundary should I consider?

Memory/identity/trust state is stored by Lithtrix; some local client-side signing is used for delegation. Recorded sensitive-access context: Persistent agent identity; Memory contents; Delegation credentials.

What limitations and risks should I check before use?

Identity and delegation primitives can expand agent authority; protect keys and review delegated scope. Some browse/search operations are metered. Swarm/delegation features create real identity/authority state. Exact privacy/retention for stored memory was not fully established here. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.