Titan Frameworks (LangChain, LlamaIndex, Ollama, XRPL)
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| X402_PAY_TO | No | Ethereum (Base) address to receive USDC payments when x402 is enabled. | |
| GITHUB_TOKEN | No | Optional GitHub token to raise API rate limits when refreshing docs. | |
| X402_ENABLED | No | Set to 'true' to enable x402 micropayments for HTTP tool calls. Defaults to off. | false |
| XRPL_NETWORK | No | XRPL network identifier, e.g. 'xrpl:1' for mainnet. | |
| X402_XRPL_LIVE | No | Set to 'true' to enable live verification/settlement of XRP/RLUSD proofs via the facilitator. | |
| XRPL_PRICE_DROPS | No | Price in XRP drops (e.g. '1000') for XRP/RLUSD payment. | |
| XRPL_PAY_TO_ADDRESS | No | XRPL address to receive XRP/RLUSD payments. | |
| XRPL_FACILITATOR_URL | No | URL of the T54 facilitator used for XRP/RLUSD proof verification and settlement. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| review_framework_codeA | Scan source against known dead APIs (LLMChain, initialize_agent, ServiceContext, ripple-lib, …) and return each hit with replacement plus a unified-diff hunk. Use before running agent-written code; diagnose_framework_error is for after a stack trace. Does not execute or submit. Paid tools/call: $0.001 USDC or 1000 drops XRP; catalog-backed, not LLM-invented. |
| rewrite_framework_codeA | Apply conservative catalog rewrites (imports/identifiers) to a snippet and return the patched file plus a full unified diff. Use when review_framework_code found hits and you want an applyable file. Leftover lists unsafe call-site transforms (e.g. LLMChain(...)) that stay for a human/agent. Does not execute or submit. Paid tools/call: $0.001 USDC or 1000 drops XRP. |
| diagnose_framework_errorA | Match a stack trace or exception against known deprecated APIs for langchain, llamaindex, ollama, or xrpl and return the replacement plus a fix. Use only when you have an error_log; matched=false means no catalog hit — then search_ai_framework_docs with the failing symbol. Lint source before it crashes with review_framework_code. Not for happy-path syntax (fetch_latest_syntax). Paid tools/call: $0.001 USDC or 1000 drops XRP; read-only, does not execute code. |
| resolve_symbolA | Map an API name to the current package, install line, import, and call shape (ChatOpenAI, create_agent, VectorStoreIndex, xrpToDrops, …). Use when you know the symbol but not where it lives. Prefer search_ai_framework_docs for concepts and fetch_latest_syntax for topic snippets. Paid tools/call: $0.001 USDC or 1000 drops XRP; catalog-backed. |
| fetch_working_exampleA | Fetch one complete runnable file (filename, install/run, source) for a goal such as agent, rag, chat, payment, or rlusd. Use when fetch_latest_syntax snippets are too small to execute. matched=false means no catalog example — then fetch_latest_syntax. Paid tools/call: $0.001 USDC or 1000 drops XRP; does not execute the example. |
| fetch_latest_syntaxA | Curated working imports, snippets, and migration notes for one topic (agents, rag, wallet, payment, trustlines, …). Use when writing or migrating a fragment; unknown topics fall back to related doc chunks instead of failing. Prefer fetch_working_example for a complete runnable file, search_ai_framework_docs for open-ended lookup, and diagnose_framework_error for exceptions. Paid tools/call: $0.001 USDC or 1000 drops XRP; read-only catalog. |
| search_ai_framework_docsA | Keyword search over a local Markdown index for langchain, llamaindex, ollama, or xrpl; returns compact chunks and never live-crawls. Use for concepts, symbols, or questions; hitCount 0 means no match — shorten the query. Do not use for stack traces (diagnose_framework_error), import/package lookup (resolve_symbol), or copy-paste current syntax (fetch_latest_syntax). Paid tools/call: $0.001 USDC or 1000 drops XRP. |
| draft_xrpl_intent_txA | Draft a typed xrpl.js / xrpl-py skeleton for payment, trustline, rlusd, or channel, plus required fields and common tec/tem failure codes. Use when building an XRPL tx; never submits, signs, or moves funds. Prefer fetch_working_example for a full script and review_framework_code to lint Amount/address mistakes. Paid tools/call: $0.001 USDC or 1000 drops XRP. |
| list_supported_frameworksA | List the framework ids this server covers (langchain, llamaindex, ollama, xrpl) with display names, aliases, homepages, and catalog topics. Use when you do not know which framework string to pass. Free tools/call (no x402). Not a docs search (search_ai_framework_docs) and not a deprecation dump (list_known_deprecations). Catalog-backed. |
| list_known_deprecationsA | Return the known-deprecated API catalog (id, old API, replacement, fix) for one framework or all four at once. Use when you want the full deprecation list without a stack trace or source snippet. Prefer diagnose_framework_error when you have an error_log and review_framework_code when you have code. Paid tools/call: $0.001 USDC or 1000 drops XRP; catalog-backed, does not execute code. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| migrate_framework_code | Review then rewrite a snippet against current LangChain, LlamaIndex, Ollama, or XRPL APIs. Use when you have source, not a stack trace. |
| diagnose_stack_trace | Match a traceback to a known deprecated API and return the replacement. Use only when you have an error_log. |
| start_from_example | Fetch a complete runnable file for a goal such as agent, rag, chat, payment, or rlusd. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| index-status | How many chunks are indexed per framework |
TDQS
Scored across 10 tools
Each tool targets a distinct stage or granularity: source review, rewrite, error diagnosis, symbol resolution, examples, syntax, docs, XRPL drafting, framework listing, and deprecation listing. Descriptions explicitly steer between potentially overlapping tools, leaving little ambiguity.
All tool names follow a consistent snake_case verb_object pattern, with clear objects like framework_code, framework_error, symbol, working_example, and known_deprecations. Repeated verbs are paired with distinct objects, making the naming predictable.
Ten tools is well-scoped for a multi-framework migration and deprecation assistant. Each tool has a clear role, and no tool feels redundant or missing.
The toolset covers the full consult/refactor workflow: scan source, apply safe rewrites, diagnose errors, resolve symbols, fetch examples/syntax/docs, draft XRPL transactions, and enumerate framework/deprecation catalogs. Tools cross-reference next steps, so agents are not left at dead ends.