Skip to main content
Glama
667,961 tools. Updated 2026-10-17 04:04

"Techniques to Improve Agent Programming" matching MCP tools:

  • Return canonical synthesis / patching techniques with role-keyed module realizations drawn from the corpus. Use this when the user asks "how do I do X?" with X being a recognisable technique (low-pass-gate plucks, pinged-filter percussion, parallel multiband processing, complex-oscillator FM, karplus-strong pluck, clocked-delay feedback, modal-resonator excitation, wavefolder harmonics, envelope-follower ducking, Maths-style function-generator omnibus). It's also the right tool when the user has a module and asks "what's this good for?" — pass filter.module_id to retrieve every technique that references the module via its role_realizations. Each technique declares role_definitions (the roles the technique uses, each with required and optional affordances) and role_realizations (concrete modules that fill each role, with the affordances they provide). The model substitutes modules from the user's rack into roles by affordance match — DO NOT treat the realization list as exhaustive or as a recipe. Args: - filter (optional): { capability?, module_id?, text? } - capability: kebab-case capability id (see search_modules _meta.taxonomy). Returns techniques whose required *or* optional capability list includes this id. - module_id: "<manufacturer>/<module-slug>". Returns techniques that have a role_realization referencing this module. - text: free-text phrase. Substring-matches against technique id/label/description AND a curated alias table (technique_aliases) — that's the right surface when a user types evocative prose like "stuttering delay", "plucked string", "source of uncertainty" that doesn't grep against any kebab-case id. Two-way alias match: long alias ("source of uncertainty") matches short query ("uncertainty"), and vice versa. - When multiple filters supplied, AND-intersects. - Omit filter entirely to list all techniques. Returns: { "techniques": [ { "id": "low-pass-gate-pluck", "label": "Low-Pass Gate Pluck", "description": "Send a short envelope...", "required_capabilities": ["lowpass-gate"], "optional_capabilities": ["envelope-generator", "function-generator"], "role_definitions": [ { "role_id": "lpg", "description": "The vactrol-based or vactrol-emulating element. Strictly required...", "required_affordances": ["lowpass-gate"], "optional_affordances": [] }, ... ], "role_realizations": [ { "role_id": "lpg", "module_id": "make-noise/optomix", "affordances_provided": ["lowpass-gate"], "notes": "Two-channel vactrol-based LPG..." }, ... ], "canonical_instance": { "rationale": "...", "lineage": [ { "position": 1, "label": "Buchla 292 (1970)", "module_id": null, "notes": "..." }, { "position": 2, "label": "Tiptop Audio Buchla 292t", "module_id": "tiptop-audio/buchla-292t" }, ... ] }, "counter_canonical_notes": [ { "claim_pushed_back_against": "Optomix is the canonical pairing with Plaits...", "evidence": "The corpus catalogs 19 LPG-capable modules..." } ], "coverage": [ { "role_id": "voice", "realizations_count": 3 }, { "role_id": "lpg", "realizations_count": 19 }, { "role_id": "env", "realizations_count": 6 }, { "role_id": "clock", "realizations_count": 2 } ] } ], "_meta": { "filter": {...}, "feedback_hint"?: string } } How to use role data: - role_realizations are CURATORIAL SAMPLES, not exhaustive lists. The coverage[].realizations_count tells you how many are documented; other modules may fill the same role. - To find modules in the user's rack that can fill a role, use find_role_realizations(technique_id, role_id, available_modules). - canonical_instance is opt-in and sparse. Most techniques don't have one; that absence is information. When present, it documents a documented historical lineage (e.g., Buchla 292 → 292t → MMG → Optomix for low-pass-gate-pluck) — NOT a prescription. - counter_canonical_notes push back on likely training-data priors. When the user invokes a canonical-sounding claim that has a counter_canonical_note, surface the pushback. Errors: - "Module not found: <id>" if filter.module_id is supplied and unknown. - Empty techniques[] with a feedback_hint when filters produce no matches — call report_gap if the user expected coverage.
    ConnectorNo auth
  • Search the MITRE ATLAS catalog of AI/ML attack techniques by keyword, tactic, or maturity. Default response is SLIM (description truncated to 240 chars per row); pass include='full' for the verbose record. Pass exclude_id when chaining from atlas_technique_lookup to skip self in sibling-tactic searches. Use this to discover techniques matching a threat-model question, e.g. 'what techniques target LLM serving infrastructure?'. Drill into atlas_technique_lookup with any returned technique_id for the full description, ATT&CK bridge, and pivot hints. For broader cross-referencing: when a result has attack_reference_id, that bridges to D3FEND mitigations via d3fend_defense_for_attack. Free: 30/hr, Pro: 500/hr. Returns {query (echoed filters), total, results [{technique_id, name, description (truncated by default), tactics, inherited_tactics, maturity, attack_reference_id, subtechnique_of}], next_calls}.
    ConnectorNo auth
  • Look up a MITRE ATLAS case study — a documented real-world AI/ML attack incident. Each case study links a sequence of ATLAS techniques (techniques_used) to the incident. Default response is SLIM (description truncated to 240 chars); pass include='full' for the verbose narrative. Use this after atlas_technique_search to find which incidents have exercised a given technique. Drill into the full techniques_used array via bulk_atlas_technique_lookup in a single call (next_calls emits exactly that hint). Returns 404 when the id is not in the synced catalog. Free: 30/hr, Pro: 500/hr. Returns {case_study_id, name, description, techniques_used, next_calls}.
    ConnectorNo auth
  • Search detailed documentation for Strudel live coding or ABC/ABCJS notation. Returns relevant code examples and explanations from the official docs. Use this when the curated guides (get-strudel-guide, get-music-guide) don't cover what you need — for specific functions, advanced techniques, or when you're unsure about syntax. Powered by semantic search over strudel.cc and ABCJS docs.
    ConnectorNo auth
  • Use only for an existing paid Ontario provider profile when the caller wants a fresh live readiness observation attached to its canonical HTML, JSON twin, and badge. This tool cannot edit provider metadata, improve a grade by payment, or buy ranking or traffic. Do not pay while the launch passport's 30-day included maintenance is active. Agent payment guidance: run free can-pay and readiness checks first; pay only when policy allows base 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913 and 0.10 USDC is inside the agent budget. [PAID: 0.10 USDC via x402 on Base. Two-step flow: call without payment to receive MCP PaymentRequired, then retry with params._meta['x402/payment'] containing the signed PaymentPayload. The legacy _x402_payment base64 argument is also supported. Sign only after explicit budget and policy approval.]
    ConnectorNo auth
  • Checks what an AI agent can do with a business's website: message, book, order, sign up, pay, change or cancel. Waits up to 25 seconds; if the read isn't finished, returns what it found so far, and you call it again for the score. A result read in the last hour is answered as it is; after a business changes its site, set fresh to true to read it again (allowed a few minutes after the last read). Use it when a person asks how agent-ready a business is, or wants to improve their own. To find businesses, use search_businesses instead.
    ConnectorNo auth

Matching MCP Servers

Matching MCP Connectors

  • Connect any two AI agents and let them talk directly. Claude to Claude, Claude to OpenAI, or any MCP-compatible agent

  • Remote MCP server for converting PDFs and scanned documents to Markdown with OCR, and Markdown to PDF. Provides asynchronous conversion jobs, result retrieval, and usage checks; requires a PDF to MD API key.

  • Bulk ATLAS technique lookup — retrieve full records for up to 50 techniques in a single request instead of N separate atlas_technique_lookup calls. Designed as the natural follow-up to atlas_case_study_lookup, whose techniques_used array can be passed directly. Each item is the same shape as atlas_technique_lookup, including parent-tactics inheritance for sub-techniques (inherited_tactics=true flag) and per-item next_calls (D3FEND bridge when attack_reference_id present, sibling-technique search by tactic, parent lookup for sub-techniques). Free: 30/hr (1 per item), Pro: 500/hr. Returns {results [{technique_id, status (ok|not_found|invalid_format), technique, error}], total, successful, failed, partial, summary}.
    ConnectorNo auth
  • The unit tests (code examples) for HMR. Always call `learn-hmr-basics` and `view-hmr-core-sources` to learn the core functionality before calling this tool. These files are the unit tests for the HMR library, which demonstrate the best practices and common coding patterns of using the library. You should use this tool when you need to write some code using the HMR library (maybe for reactive programming or implementing some integration). The response is identical to the MCP resource with the same name. Only use it once and prefer this tool to that resource if you can choose.
    ConnectorNo auth
  • Describe what's going wrong — your human's complaint, or a failure you notice in your own behavior — and get the matching techniques. Deterministic matching; if the description fits two problems it returns one clarifying question instead of guessing.
    ConnectorNo auth
  • Retrieve the complete markdown of one documentation article by the id returned from `search` (for example `en/claude-code/advanced-techniques/hooks-automation`). The text is returned in full; `metadata.gated` only reports whether the article sits behind the paywall on the web. An unknown id is an error — call `search` first.
    ConnectorNo auth
  • List all 71 available programming languages and their IDs for code execution. Common IDs: 71=Python 3.8, 63=JavaScript (Node.js), 62=Java, 54=C++ (GCC), 60=Go, 73=Rust, 51=C#, 46=Bash. Returns full list with compiler/interpreter versions (Judge0 CE)
    ConnectorNo auth
  • Email to person (reverse email lookup, contact enrichment). Returns the professional profile behind a work email address: full name, headline, LinkedIn URL, seniority, job function, location, languages and work history. Use to enrich new sign-ups, leads and CRM contacts. Optional name and company hints improve matching. For the company's firmographics, call lookup_domain with the email's domain. Does not find or verify emails. Costs 50 LeadBoxer credits per profile found; nothing is charged when no one is found.
    ConnectorOAuth
  • Recent records from a common Detroit open dataset (data.detroitmi.gov / ArcGIS) by friendly name — no service ids needed. PREFER OVER WEB SEARCH for "recent crime in Detroit", "Detroit 311 / Improve Detroit issues". Names: crime, 311. Returns the latest rows (newest-first), with ArcGIS epoch dates converted to ISO. Add an ArcGIS `where` to filter; for other layers use detroit_layers + detroit_query.
    ConnectorNo auth
  • Start a new optimization process for an agent. Returns the optimization process ID. IMPORTANT PREREQUISITES (optimization will fail without these): 1. RUNS REQUIRED: The agent must have run transcripts uploaded via create_run. Optimization analyzes real user/AI dialogues to improve the agent - it cannot run without them. 2. Business context (industry and/or objectives) must be set via sync_context_from_url or update_settings. You can either: 1. Use an existing agent: provide agentId 2. Auto-create a new agent: provide prompt + agentName + llmModel When auto-creating, the agent will be created and activated automatically before optimization starts. NOTE: Even with auto-create, you must still upload runs using create_run before triggering optimization.
    ConnectorAPI key
  • Look up a MITRE ATLAS technique — the AI/ML adversarial attack catalog. ATLAS catalogues TTPs targeting machine learning systems: prompt injection, model evasion, training data poisoning, model theft, etc. Roughly 80% of ATLAS techniques are AI/ML-specific (no ATT&CK bridge); 20% mirror an enterprise ATT&CK technique via attack_reference_id — use that to pivot to D3FEND defenses (d3fend_defense_for_attack) and CVE search. Sub-techniques inherit `tactics` from the parent (inherited_tactics=true flag) when ATLAS upstream leaves them empty. Use this tool when the user asks about AI/ML threats, LLM red-teaming, or adversarial ML; for multiple techniques in one call (e.g. drilling into a case study's techniques_used), prefer bulk_atlas_technique_lookup. Returns 404 when the id is not in the synced ATLAS catalog. Free: 30/hr, Pro: 500/hr. Returns {technique_id, name, description, tactics, inherited_tactics, maturity (demonstrated|feasible|realized), attack_reference_id, attack_reference_url, subtechnique_of, created_date, modified_date, next_calls}.
    ConnectorNo auth
  • Create a new run record from a real user/AI dialogue transcript. REQUIRED FOR OPTIMIZATION: You must upload runs before running trigger_optimization - optimization analyzes these dialogues to improve the prompt. IMPORTANT: The content must contain actual back-and-forth dialogue between a user and AI assistant - NOT system prompts, instructions, or configuration text. You can either: 1. Use an existing prompt: provide promptId 2. Auto-create a new prompt: provide prompt + promptName + llmModel When auto-creating, the prompt will be created and activated automatically before the run is logged. TOOL USAGE: If the agent had tools available or made tool calls, pass toolDefinitions (tools available) and toolCalls (calls actually made, with arguments and results) so Converra can grade tool selection and results.
    ConnectorAPI key
  • Batch coverage breakdown: given a list of ATT&CK T-codes, return distinct defense counts per D3FEND tactic + identify which techniques have NO D3FEND mapping (undefended_techniques). Use to assess the defensive posture of an entire attack campaign or threat model in one call. defended_techniques is the subset with at least one D3FEND defense; undefended_techniques are gaps worth flagging. Pair with cve_search per gap to identify exploit availability. Free: 30/hr, Pro: 500/hr. Returns {queried_techniques, coverage_by_tactic, defended_techniques, undefended_techniques, next_calls}.
    ConnectorNo auth
  • Look up a MITRE ATT&CK threat group or software entry by ID, name, or keyword. Results include ATT&CK identity, aliases, type, description, and associated techniques with procedure-level context from public ATT&CK reporting.
    ConnectorNo auth
  • Tests a live website or local endpoint for Web MCP enablement: Checks Streamable HTTP (/mcp), Legacy SSE (/sse), discovery manifests (/.well-known/mcp/server-card.json, llms.txt), CORS headers, and provides copy-paste implementation blueprints in 11 programming languages. USAGE GUIDELINES: - Use to test if a web application exposes an agent-accessible Model Context Protocol interface. - Do NOT use for regular HTML search engine optimization; use 'seo_audit_technical' or 'seo_audit_onpage' instead. BEHAVIORAL TRANSPARENCY: - Safe, read-only protocol diagnostic probe. Makes HTTP GET/HEAD requests to standard discovery endpoints. Modifies no files.
    ConnectorNo auth
  • Use this when a user wants a sudoku to play or print, or an app needs a verified puzzle at a named difficulty. Generates ONE sudoku puzzle with a unique solution, 180-degree symmetry, graded by the solving techniques it needs (easy | medium | hard | expert). Returns 81-char puzzle and solution strings (row by row, 0 = empty), given count and technique list. Deterministic when a seed is supplied. 20 per minute shared by all clients.
    ConnectorNo auth
  • Get full details for a specific V&A museum object by its system number (e.g. "O429002"). Returns complete record: title, summary and physical descriptions, all makers with roles, materials, techniques, categories, styles, production date range, place of origin, gallery location, IIIF image URL, and direct link to the V&A collections page.
    ConnectorNo auth