# io.github.Sandeeprdy1729/timps (npm · @timps-ai/timps-mcp)

Persistent memory with contradiction detection, burnout monitoring, and 69 intelligence tools.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-23

## Components

- npm · `@timps-ai/timps-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/sandeeprdy1729-timps/timps-ai-timps-mcp.md), [page](https://verifymcp.io/servers/sandeeprdy1729-timps/timps-ai-timps-mcp)

## Channel facts

- Registry: `npm`
- Package: `@timps-ai/timps-mcp`
- Version: `2.0.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-23.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 46 of 160 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 3645 tokens (~52/item across 69 items; 69 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.Sandeeprdy1729/timps MCP server?

io.github.Sandeeprdy1729/timps runs locally as an npm package, launched with npx -y @timps-ai/timps-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add sandeeprdy1729-timps -- npx -y @timps-ai/timps-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "sandeeprdy1729-timps": {
      "command": "npx",
      "args": [
        "-y",
        "@timps-ai/timps-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sandeeprdy1729-timps": {
      "command": "npx",
      "args": [
        "-y",
        "@timps-ai/timps-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add sandeeprdy1729-timps -- npx -y @timps-ai/timps-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sandeeprdy1729-timps": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@timps-ai/timps-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sandeeprdy1729-timps --command npx --arg -y --arg @timps-ai/timps-mcp
```

### Hermes

```yaml
mcp_servers:
  sandeeprdy1729-timps:
    command: "npx"
    args: ["-y", "@timps-ai/timps-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "sandeeprdy1729-timps": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@timps-ai/timps-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add sandeeprdy1729-timps -t stdio -c npx -a -y @timps-ai/timps-mcp
```

### Other

```json
{
  "mcpServers": {
    "sandeeprdy1729-timps": {
      "command": "npx",
      "args": [
        "-y",
        "@timps-ai/timps-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-20 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-19 (score 53)

First indexed and scored.

## MCP tools (69)

### `timps_chat` (~58 tokens)

Send a message to TIMPs with full memory context. Automatically activates contradiction detection, burnout analysis, bug patterns, and other intelligence tools.

Input parameters:

- `message` (string, required): Message to send to TIMPs
- `username` (string): Optional username

### `timps_get_memories` (~28 tokens)

Get all stored memories, goals, and preferences. Use before starting a complex task.

### `timps_store_memory` (~43 tokens)

Store an important fact in TIMPs long-term memory.

Input parameters:

- `content` (string, required): Memory to store
- `importance` (number): Importance 1-5

### `timps_check_contradiction` (~41 tokens)

Check if a statement contradicts past positions or stored memories. Use before any opinion or decision.

Input parameters:

- `text` (string, required): Statement to check

### `timps_get_positions` (~18 tokens)

List all tracked positions with conflict counts.

### `timps_check_regret` (~30 tokens)

Warn before repeating a past regretted decision.

Input parameters:

- `decision` (string, required): Decision being considered

### `timps_log_decision` (~57 tokens)

Log a decision outcome to build the Regret Oracle knowledge base.

Input parameters:

- `description` (string, required): The decision made
- `outcome` (string): What happened
- `regret_score` (number): Regret 0-1

### `timps_burnout_analyze` (~28 tokens)

Analyze burnout risk vs personal baseline. Use when user mentions stress or exhaustion.

### `timps_record_signal` (~47 tokens)

Log a behavioral signal for burnout tracking.

Input parameters:

- `signal_type` (string, required): focus_hours | energy_level | enthusiasm_score | commits_per_day
- `value` (number, required): Signal value

### `timps_warn_bug_pattern` (~39 tokens)

Check if coding context matches personal bug triggers. Use before writing code under pressure.

Input parameters:

- `context` (string, required): Current coding context and conditions

### `timps_record_bug` (~54 tokens)

Record a bug to build personal pattern profile.

Input parameters:

- `bug_type` (string, required): race_condition | null_pointer | off_by_one | memory_leak | etc.
- `trigger_context` (string): Context when bug appeared

### `timps_check_tech_debt` (~49 tokens)

Check if code pattern matches past codebase incidents. Use during code review.

Input parameters:

- `pattern` (string, required): Code pattern or approach
- `project_id` (string): Project ID

### `timps_record_incident` (~56 tokens)

Record a production incident to build pattern library.

Input parameters:

- `incident_type` (string): Incident type
- `pattern` (string, required): Code pattern that caused the incident
- `time_to_debug_hrs` (number): Debug hours

### `timps_lookup_api` (~39 tokens)

Look up known quirks for an API before using it.

Input parameters:

- `api_name` (string, required): API name: Stripe, GitHub, etc.

### `timps_record_api_quirk` (~60 tokens)

Save a discovered API quirk for future reference.

Input parameters:

- `api_name` (string, required): API name
- `endpoint` (string): Specific endpoint
- `quirk` (string, required): The undocumented behavior
- `severity` (string)

### `timps_extract_commitments` (~58 tokens)

Extract commitments from meeting notes using regex + participant detection. Use after any meeting. Returns structured commitments with owner and deadline.

Input parameters:

- `meeting_notes` (string, required): Raw meeting notes or transcript
- `meeting_title` (string): Meeting name

### `timps_get_pending_commitments` (~27 tokens)

List all pending commitments not yet completed. Use as a daily check-in.

### `timps_complete_commitment` (~59 tokens)

Mark a commitment as completed. Accepts an id prefix (first 12 chars shown by timps_get_pending_commitments).

Input parameters:

- `id_prefix` (string, required): Commitment id prefix (first 12 chars from timps_get_pending_commitments)

### `timps_record_mention` (~55 tokens)

Record that a person was mentioned in some context. Builds the relationship profile that powers drift alerts.

Input parameters:

- `context` (string, required): What was said about them or in what context
- `name` (string, required): Person name

### `timps_relationship_check` (~53 tokens)

Check relationship health and drift alerts. Use when user mentions a person. Returns drift alerts for contacts not mentioned in 90+ days.

Input parameters:

- `contact_name` (string): Person name — omit for all drift alerts

### `timps_log_past_decision` (~88 tokens)

Log a past decision with its outcome. Seeds the simulation model used by timps_simulate_decision.

Input parameters:

- `context` (string, required): Context surrounding the decision
- `decision` (string, required): The decision that was made
- `outcome` (string, required): How it turned out
- `regret_score` (number, required): Regret 0-1, where 1 = catastrophic

### `timps_simulate_decision` (~67 tokens)

Simulate future outcomes for a decision based on actual history. Uses Jaccard similarity to find similar past decisions and votes weighted by regret.

Input parameters:

- `horizon_months` (number): Months ahead (default 12)
- `scenario` (string, required): Decision or situation to simulate

### `timps_ingest_manifesto_signal` (~55 tokens)

Add a behavioral observation to the manifesto corpus. Mines from positions, decisions, and architecture insights automatically on init.

Input parameters:

- `text` (string, required): Behavioral signal (what was decided, shipped, regretted, etc.)

### `timps_get_manifesto` (~38 tokens)

Get the Living Manifesto — actual values derived from behavioral patterns, not stated beliefs. Mines from positions, decisions, and architecture insights.

### `timps_chronos_ingest` (~115 tokens)

Ingest a signal into Chronos Veil with layered persistence. Auto-classifies into knowledge/memory/wisdom/intelligence with entity linking.

Input parameters:

- `content` (string, required): The signal or event to ingest
- `entity` (string): Primary entity identifier
- `source_module` (string, required): Source: timps-code, timps-vscode, timps-mcp, reflection, etc.
- `tags` (array): Entity tags: code, bug, tech-debt, api, burnout, relationship

### `timps_chronos_query` (~76 tokens)

Query Chronos Veil with the multi-tool resolution agent. Resolves conflicts and produces compact temporal summaries.

Input parameters:

- `limit` (number): Max events to return (default 8)
- `query` (string, required): Temporal query (e.g. "how has my bug patterns evolved?", "what API decisions were superseded?")

### `timps_chronos_stats` (~32 tokens)

Get Chronos Veil statistics: event counts by layer, recent events, and entity graph edges.

### `timps_nexus_ingest` (~112 tokens)

Ingest a signal into NexusForge episodic memory. Builds hybrid graph nodes with time-aware gists and factual links. Use after coding sessions, decisions, or notable events.

Input parameters:

- `content` (string, required): The signal or event to ingest
- `source_module` (string, required): Source: timps-code, timps-vscode, timps-mcp, cli, etc.
- `tags` (array): Entity tags: code, bug, tech-debt, api, burnout, relationship, regret

### `timps_nexus_query` (~72 tokens)

Query NexusForge episodic memory with agentic iterative retrieval. Returns episodic nodes with spatiotemporal context, refusal when evidence is insufficient.

Input parameters:

- `query` (string, required): Episodic query (e.g. "what coding sessions led to burnout signals?", "show my regret patterns around API decisions")

### `timps_nexus_stats` (~29 tokens)

Get NexusForge episodic memory statistics: node counts, edge counts, and source breakdown.

### `timps_nexus_graph` (~53 tokens)

Get the episodic graph structure (nodes + edges) for visualization. Returns recent episodic nodes and their temporal/causal links.

Input parameters:

- `limit` (number): Max nodes to return (default 30)

### `timps_synapse_ingest` (~117 tokens)

Ingest a signal into SynapseMetabolon spreading activation graph. Classifies into interaction/reasoning/audit layers with automatic entity linking and activation spread.

Input parameters:

- `content` (string, required): The signal or event to ingest
- `entity` (string): Primary entity identifier
- `source_module` (string, required): Source: timps-code, timps-vscode, timps-mcp, reflection, etc.
- `tags` (array): Entity tags: code, bug, tech-debt, api, burnout, relationship

### `timps_synapse_query` (~89 tokens)

Query SynapseMetabolon with spreading activation. Spreads from seed nodes through relational edges, runs metabolic cycle, and returns activated nodes with confidence scores.

Input parameters:

- `limit` (number): Max activated nodes to return (default 10)
- `query` (string, required): Metabolic graph query (e.g. "how do my coding sessions relate to burnout?", "show patterns around API decisions")

### `timps_synapse_stats` (~32 tokens)

Get SynapseMetabolon statistics: node counts, edge counts, layer breakdown, and average activation.

### `timps_synapse_graph` (~48 tokens)

Get the metabolic graph structure (nodes + edges) for visualization. Returns nodes with activation scores and layer information.

Input parameters:

- `limit` (number): Max nodes to return (default 30)

### `timps_synapse_consolidate` (~43 tokens)

Run a metabolic consolidation cycle. Consolidates high-activation nodes, audits low-utility nodes, refreshes stale nodes, and decays inactive ones.

### `timps_get_session_history` (~47 tokens)

Retrieve what you were working on in recent sessions. Use before starting a task to restore context.

Input parameters:

- `days_back` (integer): How many days back (default: 7)

### `timps_get_architecture_decisions` (~47 tokens)

Retrieve past architecture decisions and design choices. Use when making structural code decisions.

Input parameters:

- `topic` (string): Filter by topic (e.g. auth, database, state)

### `timps_get_code_patterns` (~33 tokens)

Retrieve personal coding patterns and conventions I always use.

Input parameters:

- `context` (string): Filter by context or language

### `timps_record_pattern` (~54 tokens)

Store a reusable code pattern or convention for future recall.

Input parameters:

- `pattern` (string, required): The code pattern or convention to store
- `tags` (array): Tags like ["typescript", "react", "error-handling"]

### `timps_get_patterns_for_context` (~49 tokens)

Retrieve code patterns relevant to the current file or task context.

Input parameters:

- `file_path` (string): Current file path
- `task_description` (string, required): What you are trying to do

### `timps_detect_architecture_drift` (~49 tokens)

Compare current code structure against past architectural decisions and detect drift.

Input parameters:

- `current_patterns` (array, required): Patterns observed in current codebase
- `project_id` (string): Project ID

### `timps_predict_bug_risk` (~53 tokens)

Predict bug risk for a planned change based on past incident history.

Input parameters:

- `change_description` (string, required): What you are about to change or add
- `files_affected` (array): Files being changed

### `timps_get_incident_timeline` (~45 tokens)

Show past incidents and bugs in a specific module or area.

Input parameters:

- `module` (string, required): Module name or area (e.g. auth, payment, queue)

### `timps_check_deployment_risk` (~36 tokens)

Check if a deployment pattern has caused issues before.

Input parameters:

- `pattern` (string, required): Deployment approach or config being used

### `timps_get_velocity_trend` (~26 tokens)

Show productivity trend — am I faster or slower this week vs baseline?

### `timps_get_context_switches` (~21 tokens)

Count and analyze context switches in current session.

### `timps_record_learning` (~39 tokens)

Store something you learned today for future reference.

Input parameters:

- `learning` (string, required): What you learned
- `topic` (string): Topic or technology

### `timps_get_shared_decisions` (~34 tokens)

Retrieve team-level architecture decisions. Scoped to the current project.

Input parameters:

- `topic` (string): Filter by topic

### `timps_record_review_pattern` (~45 tokens)

Store something you consistently flag or look for during code reviews.

Input parameters:

- `pattern` (string, required): What you always check or flag in reviews
- `severity` (string)

### `timps_temporal_query` (~99 tokens)

Query memories that were valid at a specific point in time. Use for historical reconstruction ("what did I believe on March 15?"), longitudinal tracking, or context-anchored retrieval.

Input parameters:

- `at_timestamp` (number, required): Unix epoch seconds for the point-in-time query. Use Date.now()/1000 for "now".
- `domain` (string): Filter by memory domain
- `limit` (number): Max results (default 10)

### `timps_chrono_foresight` (~97 tokens)

Run a Monte-Carlo foresight simulation to predict future risk trajectories. Use for burnout prediction ("am I heading toward burnout?"), relationship drift warnings, decision regret risk, or recurring bug likelihood.

Input parameters:

- `domain` (string, required): Which domain to simulate
- `lookback_days` (number): How many days of history to analyze (default 30)
- `steps` (number): Simulation steps (default 10)

### `timps_chrono_consolidate` (~73 tokens)

Run the Ebbinghaus adaptive consolidation pass — prunes low-importance memories that have decayed below threshold while preserving causally important nodes. Use periodically to keep memory lean and relevant.

Input parameters:

- `importance_threshold` (number): Prune memories with effective score below this (default 0.05)

### `timps_skill_shadow` (~58 tokens)

Coach using your own observed workflow patterns. Reframes VelocityTracker advice as "how YOU do this work" rather than generic tips.

Input parameters:

- `situation` (string, required): The current situation or task (e.g. "writing a hard refactor")

### `timps_log_question` (~35 tokens)

Log a question you asked. Powers CurriculumArchitect's learning-gap detection.

Input parameters:

- `question` (string, required): The question you asked

### `timps_curriculum_plan` (~38 tokens)

Generate a learning plan based on what you keep asking about vs what you've decided. High gap_score = you keep asking but never decide.

### `timps_observe_culture` (~45 tokens)

Add a decision text to the codebase culture corpus. Mines from positions, decisions, and architecture insights automatically.

Input parameters:

- `text` (string, required): Decision text or observation

### `timps_codebase_culture` (~48 tokens)

Surface the cultural norms of the codebase from stored decisions. Mines 15 hard-coded norm patterns (async/await, TypeScript, tests, REST, PostgreSQL, etc.).

### `timps_record_contribution` (~74 tokens)

Record a contribution from a team member. Preserves their decisions/patterns/incidents/quirks so the team can reference them after they leave.

Input parameters:

- `contributor` (string, required): Person name (lowercase canonical)
- `kind` (string, required): Type of contribution
- `text` (string, required): What they contributed

### `timps_mark_contributor_active` (~61 tokens)

Mark that a contributor was active on a given date. Updates their last-seen timestamp used by timps_institutional_memory.

Input parameters:

- `contributor` (string, required): Person name
- `date` (string): ISO date string (defaults to now)

### `timps_institutional_memory` (~55 tokens)

List contributors who haven't been seen in 90+ days, with their contributions preserved. Use to recover knowledge after someone leaves the team.

Input parameters:

- `contributor` (string): Specific contributor to query (omit for all dormant)

### `timps_verify_engram_chain` (~36 tokens)

Verify the integrity of the immutable memory audit trail (L10 EngramLog). Returns valid/invalid and block count.

### `timps_false_memory_check` (~74 tokens)

Score a memory's false-memory risk based on provenance, source reliability, evidence count, and age (Tool 18).

Input parameters:

- `ageDays` (number, required): Age of the memory in days
- `content` (string, required): The memory content to check
- `evidenceCount` (number, required): Number of supporting evidence entries

### `timps_explain_provenance` (~55 tokens)

Get the provenance chain for a memory — where it came from, how it was derived, and reliability scoring (Tool 20 SourceAttributor).

Input parameters:

- `memoryId` (string, required): Memory ID or content hash

### `timps_resolve_conflict` (~63 tokens)

Check for conflicts/contradictions between two memories using Jaccard similarity + sentiment analysis (Tool 21 ConflictResolver).

Input parameters:

- `memoryA` (string, required): First memory content to compare
- `memoryB` (string, required): Second memory content to compare

### `timps_audit_memory` (~42 tokens)

Run a full memory health audit — weak, contradicted, outdated, and unsourced entries with health score and recommendations (Tool 22 MemoryAuditor).

### `timps_register_trigger` (~77 tokens)

Register a prospective trigger: when a specific phrase appears in context, surface a specific memory or action (Tool 23 / L17).

Input parameters:

- `memoryId` (string, required): Memory ID to associate
- `surface` (string, required): What to surface when trigger fires
- `when` (string, required): Trigger phrase to watch for (substring match)

### `timps_reveal_bias` (~35 tokens)

Analyze memory for over/under-representation bias across saved facts (Tool 24 / L18 BiasRevealer).

### `timps_infer_schemas` (~37 tokens)

Auto-extract typed schemas from memory stream — detects repeated patterns and infers structure types (Tool 25 SchemaInferrer).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/sandeeprdy1729-timps/timps-ai-timps-mcp#diagnostics

## Score history

- 2026-08-23: 68
- 2026-08-22: 68
- 2026-08-21: 68
- 2026-08-20: 68
- 2026-08-19: 53

## Common questions

### What is the io.github.Sandeeprdy1729/timps MCP server?

io.github.Sandeeprdy1729/timps is an MCP server listed in the public MCP registry as io.github.Sandeeprdy1729/timps. Persistent memory with contradiction detection, burnout monitoring, and 69 intelligence tools. This page covers its npm package (@timps-ai/timps-mcp).

### Is the io.github.Sandeeprdy1729/timps MCP server safe to use?

io.github.Sandeeprdy1729/timps scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 August 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.Sandeeprdy1729/timps MCP server expose?

io.github.Sandeeprdy1729/timps exposes 69 tools: timps_chat, timps_get_memories, timps_store_memory, timps_check_contradiction, timps_get_positions, and 64 more. Their descriptions and schemas cost roughly 3,645 tokens of context every time the server is loaded.

### Is the io.github.Sandeeprdy1729/timps MCP server still maintained?

io.github.Sandeeprdy1729/timps is still listed as active in the MCP registry. We last reached this channel on 23 August 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.Sandeeprdy1729/timps MCP server under?

io.github.Sandeeprdy1729/timps declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@timps-ai/timps-mcp
- Socket report: https://socket.dev/npm/package/@timps-ai/timps-mcp
- Repository: https://github.com/TIMPSs/timps
- Changelog RSS feed: https://verifymcp.io/servers/sandeeprdy1729-timps/timps-ai-timps-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sandeeprdy1729-timps/timps-ai-timps-mcp.json
- HTML version of this page: https://verifymcp.io/servers/sandeeprdy1729-timps/timps-ai-timps-mcp